2005-04-17 06:20:36 +08:00
|
|
|
/*
|
|
|
|
|
* linux/kernel/exit.c
|
|
|
|
|
*
|
|
|
|
|
* Copyright (C) 1991, 1992 Linus Torvalds
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
#include <linux/mm.h>
|
|
|
|
|
#include <linux/slab.h>
|
|
|
|
|
#include <linux/interrupt.h>
|
|
|
|
|
#include <linux/module.h>
|
2006-01-12 04:17:46 +08:00
|
|
|
#include <linux/capability.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
#include <linux/completion.h>
|
|
|
|
|
#include <linux/personality.h>
|
|
|
|
|
#include <linux/tty.h>
|
2008-07-01 02:42:08 +08:00
|
|
|
#include <linux/iocontext.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
#include <linux/key.h>
|
|
|
|
|
#include <linux/security.h>
|
|
|
|
|
#include <linux/cpu.h>
|
|
|
|
|
#include <linux/acct.h>
|
2006-10-01 14:28:59 +08:00
|
|
|
#include <linux/tsacct_kern.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
#include <linux/file.h>
|
2008-04-24 19:44:08 +08:00
|
|
|
#include <linux/fdtable.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
#include <linux/binfmts.h>
|
2006-10-02 17:18:06 +08:00
|
|
|
#include <linux/nsproxy.h>
|
2006-12-08 18:38:01 +08:00
|
|
|
#include <linux/pid_namespace.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
#include <linux/ptrace.h>
|
|
|
|
|
#include <linux/profile.h>
|
|
|
|
|
#include <linux/mount.h>
|
|
|
|
|
#include <linux/proc_fs.h>
|
2007-05-09 17:34:33 +08:00
|
|
|
#include <linux/kthread.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
#include <linux/mempolicy.h>
|
2006-07-14 15:24:40 +08:00
|
|
|
#include <linux/taskstats_kern.h>
|
2006-07-14 15:24:36 +08:00
|
|
|
#include <linux/delayacct.h>
|
2007-07-17 19:03:35 +08:00
|
|
|
#include <linux/freezer.h>
|
2007-10-19 14:39:33 +08:00
|
|
|
#include <linux/cgroup.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
#include <linux/syscalls.h>
|
2005-05-01 23:59:14 +08:00
|
|
|
#include <linux/signal.h>
|
2006-03-29 08:11:18 +08:00
|
|
|
#include <linux/posix-timers.h>
|
2005-11-07 16:59:16 +08:00
|
|
|
#include <linux/cn_proc.h>
|
2006-01-10 07:59:21 +08:00
|
|
|
#include <linux/mutex.h>
|
2006-03-27 17:16:22 +08:00
|
|
|
#include <linux/futex.h>
|
2006-04-11 19:52:07 +08:00
|
|
|
#include <linux/pipe_fs_i.h>
|
2006-03-30 09:30:19 +08:00
|
|
|
#include <linux/audit.h> /* for audit_free() */
|
2006-06-25 20:47:41 +08:00
|
|
|
#include <linux/resource.h>
|
2006-08-30 02:05:56 +08:00
|
|
|
#include <linux/blkdev.h>
|
2007-05-11 13:22:37 +08:00
|
|
|
#include <linux/task_io_accounting_ops.h>
|
2008-07-26 10:45:46 +08:00
|
|
|
#include <linux/tracehook.h>
|
2009-03-30 07:50:06 +08:00
|
|
|
#include <linux/fs_struct.h>
|
CRED: Inaugurate COW credentials
Inaugurate copy-on-write credentials management. This uses RCU to manage the
credentials pointer in the task_struct with respect to accesses by other tasks.
A process may only modify its own credentials, and so does not need locking to
access or modify its own credentials.
A mutex (cred_replace_mutex) is added to the task_struct to control the effect
of PTRACE_ATTACHED on credential calculations, particularly with respect to
execve().
With this patch, the contents of an active credentials struct may not be
changed directly; rather a new set of credentials must be prepared, modified
and committed using something like the following sequence of events:
struct cred *new = prepare_creds();
int ret = blah(new);
if (ret < 0) {
abort_creds(new);
return ret;
}
return commit_creds(new);
There are some exceptions to this rule: the keyrings pointed to by the active
credentials may be instantiated - keyrings violate the COW rule as managing
COW keyrings is tricky, given that it is possible for a task to directly alter
the keys in a keyring in use by another task.
To help enforce this, various pointers to sets of credentials, such as those in
the task_struct, are declared const. The purpose of this is compile-time
discouragement of altering credentials through those pointers. Once a set of
credentials has been made public through one of these pointers, it may not be
modified, except under special circumstances:
(1) Its reference count may incremented and decremented.
(2) The keyrings to which it points may be modified, but not replaced.
The only safe way to modify anything else is to create a replacement and commit
using the functions described in Documentation/credentials.txt (which will be
added by a later patch).
This patch and the preceding patches have been tested with the LTP SELinux
testsuite.
This patch makes several logical sets of alteration:
(1) execve().
This now prepares and commits credentials in various places in the
security code rather than altering the current creds directly.
(2) Temporary credential overrides.
do_coredump() and sys_faccessat() now prepare their own credentials and
temporarily override the ones currently on the acting thread, whilst
preventing interference from other threads by holding cred_replace_mutex
on the thread being dumped.
This will be replaced in a future patch by something that hands down the
credentials directly to the functions being called, rather than altering
the task's objective credentials.
(3) LSM interface.
A number of functions have been changed, added or removed:
(*) security_capset_check(), ->capset_check()
(*) security_capset_set(), ->capset_set()
Removed in favour of security_capset().
(*) security_capset(), ->capset()
New. This is passed a pointer to the new creds, a pointer to the old
creds and the proposed capability sets. It should fill in the new
creds or return an error. All pointers, barring the pointer to the
new creds, are now const.
(*) security_bprm_apply_creds(), ->bprm_apply_creds()
Changed; now returns a value, which will cause the process to be
killed if it's an error.
(*) security_task_alloc(), ->task_alloc_security()
Removed in favour of security_prepare_creds().
(*) security_cred_free(), ->cred_free()
New. Free security data attached to cred->security.
(*) security_prepare_creds(), ->cred_prepare()
New. Duplicate any security data attached to cred->security.
(*) security_commit_creds(), ->cred_commit()
New. Apply any security effects for the upcoming installation of new
security by commit_creds().
(*) security_task_post_setuid(), ->task_post_setuid()
Removed in favour of security_task_fix_setuid().
(*) security_task_fix_setuid(), ->task_fix_setuid()
Fix up the proposed new credentials for setuid(). This is used by
cap_set_fix_setuid() to implicitly adjust capabilities in line with
setuid() changes. Changes are made to the new credentials, rather
than the task itself as in security_task_post_setuid().
(*) security_task_reparent_to_init(), ->task_reparent_to_init()
Removed. Instead the task being reparented to init is referred
directly to init's credentials.
NOTE! This results in the loss of some state: SELinux's osid no
longer records the sid of the thread that forked it.
(*) security_key_alloc(), ->key_alloc()
(*) security_key_permission(), ->key_permission()
Changed. These now take cred pointers rather than task pointers to
refer to the security context.
(4) sys_capset().
This has been simplified and uses less locking. The LSM functions it
calls have been merged.
(5) reparent_to_kthreadd().
This gives the current thread the same credentials as init by simply using
commit_thread() to point that way.
(6) __sigqueue_alloc() and switch_uid()
__sigqueue_alloc() can't stop the target task from changing its creds
beneath it, so this function gets a reference to the currently applicable
user_struct which it then passes into the sigqueue struct it returns if
successful.
switch_uid() is now called from commit_creds(), and possibly should be
folded into that. commit_creds() should take care of protecting
__sigqueue_alloc().
(7) [sg]et[ug]id() and co and [sg]et_current_groups.
The set functions now all use prepare_creds(), commit_creds() and
abort_creds() to build and check a new set of credentials before applying
it.
security_task_set[ug]id() is called inside the prepared section. This
guarantees that nothing else will affect the creds until we've finished.
The calling of set_dumpable() has been moved into commit_creds().
Much of the functionality of set_user() has been moved into
commit_creds().
The get functions all simply access the data directly.
(8) security_task_prctl() and cap_task_prctl().
security_task_prctl() has been modified to return -ENOSYS if it doesn't
want to handle a function, or otherwise return the return value directly
rather than through an argument.
Additionally, cap_task_prctl() now prepares a new set of credentials, even
if it doesn't end up using it.
(9) Keyrings.
A number of changes have been made to the keyrings code:
(a) switch_uid_keyring(), copy_keys(), exit_keys() and suid_keys() have
all been dropped and built in to the credentials functions directly.
They may want separating out again later.
(b) key_alloc() and search_process_keyrings() now take a cred pointer
rather than a task pointer to specify the security context.
(c) copy_creds() gives a new thread within the same thread group a new
thread keyring if its parent had one, otherwise it discards the thread
keyring.
(d) The authorisation key now points directly to the credentials to extend
the search into rather pointing to the task that carries them.
(e) Installing thread, process or session keyrings causes a new set of
credentials to be created, even though it's not strictly necessary for
process or session keyrings (they're shared).
(10) Usermode helper.
The usermode helper code now carries a cred struct pointer in its
subprocess_info struct instead of a new session keyring pointer. This set
of credentials is derived from init_cred and installed on the new process
after it has been cloned.
call_usermodehelper_setup() allocates the new credentials and
call_usermodehelper_freeinfo() discards them if they haven't been used. A
special cred function (prepare_usermodeinfo_creds()) is provided
specifically for call_usermodehelper_setup() to call.
call_usermodehelper_setkeys() adjusts the credentials to sport the
supplied keyring as the new session keyring.
(11) SELinux.
SELinux has a number of changes, in addition to those to support the LSM
interface changes mentioned above:
(a) selinux_setprocattr() no longer does its check for whether the
current ptracer can access processes with the new SID inside the lock
that covers getting the ptracer's SID. Whilst this lock ensures that
the check is done with the ptracer pinned, the result is only valid
until the lock is released, so there's no point doing it inside the
lock.
(12) is_single_threaded().
This function has been extracted from selinux_setprocattr() and put into
a file of its own in the lib/ directory as join_session_keyring() now
wants to use it too.
The code in SELinux just checked to see whether a task shared mm_structs
with other tasks (CLONE_VM), but that isn't good enough. We really want
to know if they're part of the same thread group (CLONE_THREAD).
(13) nfsd.
The NFS server daemon now has to use the COW credentials to set the
credentials it is going to use. It really needs to pass the credentials
down to the functions it calls, but it can't do that until other patches
in this series have been applied.
Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: James Morris <jmorris@namei.org>
Signed-off-by: James Morris <jmorris@namei.org>
2008-11-14 07:39:23 +08:00
|
|
|
#include <linux/init_task.h>
|
perf: Do the big rename: Performance Counters -> Performance Events
Bye-bye Performance Counters, welcome Performance Events!
In the past few months the perfcounters subsystem has grown out its
initial role of counting hardware events, and has become (and is
becoming) a much broader generic event enumeration, reporting, logging,
monitoring, analysis facility.
Naming its core object 'perf_counter' and naming the subsystem
'perfcounters' has become more and more of a misnomer. With pending
code like hw-breakpoints support the 'counter' name is less and
less appropriate.
All in one, we've decided to rename the subsystem to 'performance
events' and to propagate this rename through all fields, variables
and API names. (in an ABI compatible fashion)
The word 'event' is also a bit shorter than 'counter' - which makes
it slightly more convenient to write/handle as well.
Thanks goes to Stephane Eranian who first observed this misnomer and
suggested a rename.
User-space tooling and ABI compatibility is not affected - this patch
should be function-invariant. (Also, defconfigs were not touched to
keep the size down.)
This patch has been generated via the following script:
FILES=$(find * -type f | grep -vE 'oprofile|[^K]config')
sed -i \
-e 's/PERF_EVENT_/PERF_RECORD_/g' \
-e 's/PERF_COUNTER/PERF_EVENT/g' \
-e 's/perf_counter/perf_event/g' \
-e 's/nb_counters/nb_events/g' \
-e 's/swcounter/swevent/g' \
-e 's/tpcounter_event/tp_event/g' \
$FILES
for N in $(find . -name perf_counter.[ch]); do
M=$(echo $N | sed 's/perf_counter/perf_event/g')
mv $N $M
done
FILES=$(find . -name perf_event.*)
sed -i \
-e 's/COUNTER_MASK/REG_MASK/g' \
-e 's/COUNTER/EVENT/g' \
-e 's/\<event\>/event_id/g' \
-e 's/counter/event/g' \
-e 's/Counter/Event/g' \
$FILES
... to keep it as correct as possible. This script can also be
used by anyone who has pending perfcounters patches - it converts
a Linux kernel tree over to the new naming. We tried to time this
change to the point in time where the amount of pending patches
is the smallest: the end of the merge window.
Namespace clashes were fixed up in a preparatory patch - and some
stylistic fallout will be fixed up in a subsequent patch.
( NOTE: 'counters' are still the proper terminology when we deal
with hardware registers - and these sed scripts are a bit
over-eager in renaming them. I've undone some of that, but
in case there's something left where 'counter' would be
better than 'event' we can undo that on an individual basis
instead of touching an otherwise nicely automated patch. )
Suggested-by: Stephane Eranian <eranian@google.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Paul Mackerras <paulus@samba.org>
Reviewed-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: <linux-arch@vger.kernel.org>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 18:02:48 +08:00
|
|
|
#include <linux/perf_event.h>
|
2009-04-15 07:39:12 +08:00
|
|
|
#include <trace/events/sched.h>
|
2009-09-10 01:22:48 +08:00
|
|
|
#include <linux/hw_breakpoint.h>
|
2010-10-27 05:21:23 +08:00
|
|
|
#include <linux/oom.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
#include <asm/uaccess.h>
|
|
|
|
|
#include <asm/unistd.h>
|
|
|
|
|
#include <asm/pgtable.h>
|
|
|
|
|
#include <asm/mmu_context.h>
|
|
|
|
|
|
2005-05-01 23:59:29 +08:00
|
|
|
static void exit_mm(struct task_struct * tsk);
|
|
|
|
|
|
2010-05-27 05:43:19 +08:00
|
|
|
static void __unhash_process(struct task_struct *p, bool group_dead)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
|
nr_threads--;
|
|
|
|
|
detach_pid(p, PIDTYPE_PID);
|
2010-05-27 05:43:19 +08:00
|
|
|
if (group_dead) {
|
2005-04-17 06:20:36 +08:00
|
|
|
detach_pid(p, PIDTYPE_PGID);
|
|
|
|
|
detach_pid(p, PIDTYPE_SID);
|
2006-03-29 08:11:06 +08:00
|
|
|
|
2006-04-19 13:20:16 +08:00
|
|
|
list_del_rcu(&p->tasks);
|
2009-12-18 07:27:15 +08:00
|
|
|
list_del_init(&p->sibling);
|
2010-12-08 23:22:55 +08:00
|
|
|
__this_cpu_dec(process_counts);
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
2006-03-29 08:11:25 +08:00
|
|
|
list_del_rcu(&p->thread_group);
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
2006-03-29 08:11:18 +08:00
|
|
|
/*
|
|
|
|
|
* This function expects the tasklist_lock write-locked.
|
|
|
|
|
*/
|
|
|
|
|
static void __exit_signal(struct task_struct *tsk)
|
|
|
|
|
{
|
|
|
|
|
struct signal_struct *sig = tsk->signal;
|
2010-05-27 05:43:19 +08:00
|
|
|
bool group_dead = thread_group_leader(tsk);
|
2006-03-29 08:11:18 +08:00
|
|
|
struct sighand_struct *sighand;
|
2010-05-27 05:43:17 +08:00
|
|
|
struct tty_struct *uninitialized_var(tty);
|
2006-03-29 08:11:18 +08:00
|
|
|
|
2010-02-23 09:04:50 +08:00
|
|
|
sighand = rcu_dereference_check(tsk->sighand,
|
|
|
|
|
rcu_read_lock_held() ||
|
2010-03-03 23:46:56 +08:00
|
|
|
lockdep_tasklist_lock_is_held());
|
2006-03-29 08:11:18 +08:00
|
|
|
spin_lock(&sighand->siglock);
|
|
|
|
|
|
|
|
|
|
posix_cpu_timers_exit(tsk);
|
2010-05-27 05:43:19 +08:00
|
|
|
if (group_dead) {
|
2006-03-29 08:11:18 +08:00
|
|
|
posix_cpu_timers_exit_group(tsk);
|
2010-05-27 05:43:17 +08:00
|
|
|
tty = sig->tty;
|
|
|
|
|
sig->tty = NULL;
|
2010-05-27 05:43:12 +08:00
|
|
|
} else {
|
2010-11-05 23:53:42 +08:00
|
|
|
/*
|
|
|
|
|
* This can only happen if the caller is de_thread().
|
|
|
|
|
* FIXME: this is the temporary hack, we should teach
|
|
|
|
|
* posix-cpu-timers to handle this case correctly.
|
|
|
|
|
*/
|
|
|
|
|
if (unlikely(has_group_leader_pid(tsk)))
|
|
|
|
|
posix_cpu_timers_exit_group(tsk);
|
|
|
|
|
|
2006-03-29 08:11:18 +08:00
|
|
|
/*
|
|
|
|
|
* If there is any task waiting for the group exit
|
|
|
|
|
* then notify it:
|
|
|
|
|
*/
|
2010-05-27 05:43:11 +08:00
|
|
|
if (sig->notify_count > 0 && !--sig->notify_count)
|
2006-03-29 08:11:18 +08:00
|
|
|
wake_up_process(sig->group_exit_task);
|
2007-10-17 14:27:23 +08:00
|
|
|
|
2006-03-29 08:11:18 +08:00
|
|
|
if (tsk == sig->curr_target)
|
|
|
|
|
sig->curr_target = next_thread(tsk);
|
|
|
|
|
/*
|
|
|
|
|
* Accumulate here the counters for all threads but the
|
|
|
|
|
* group leader as they die, so they can be added into
|
|
|
|
|
* the process-wide totals when those are taken.
|
|
|
|
|
* The group leader stays around as a zombie as long
|
|
|
|
|
* as there are other threads. When it gets reaped,
|
|
|
|
|
* the exit.c code will add its counts into these totals.
|
|
|
|
|
* We won't ever get here for the group leader, since it
|
|
|
|
|
* will have been the last reference on the signal_struct.
|
|
|
|
|
*/
|
sched, cputime: Introduce thread_group_times()
This is a real fix for problem of utime/stime values decreasing
described in the thread:
http://lkml.org/lkml/2009/11/3/522
Now cputime is accounted in the following way:
- {u,s}time in task_struct are increased every time when the thread
is interrupted by a tick (timer interrupt).
- When a thread exits, its {u,s}time are added to signal->{u,s}time,
after adjusted by task_times().
- When all threads in a thread_group exits, accumulated {u,s}time
(and also c{u,s}time) in signal struct are added to c{u,s}time
in signal struct of the group's parent.
So {u,s}time in task struct are "raw" tick count, while
{u,s}time and c{u,s}time in signal struct are "adjusted" values.
And accounted values are used by:
- task_times(), to get cputime of a thread:
This function returns adjusted values that originates from raw
{u,s}time and scaled by sum_exec_runtime that accounted by CFS.
- thread_group_cputime(), to get cputime of a thread group:
This function returns sum of all {u,s}time of living threads in
the group, plus {u,s}time in the signal struct that is sum of
adjusted cputimes of all exited threads belonged to the group.
The problem is the return value of thread_group_cputime(),
because it is mixed sum of "raw" value and "adjusted" value:
group's {u,s}time = foreach(thread){{u,s}time} + exited({u,s}time)
This misbehavior can break {u,s}time monotonicity.
Assume that if there is a thread that have raw values greater
than adjusted values (e.g. interrupted by 1000Hz ticks 50 times
but only runs 45ms) and if it exits, cputime will decrease (e.g.
-5ms).
To fix this, we could do:
group's {u,s}time = foreach(t){task_times(t)} + exited({u,s}time)
But task_times() contains hard divisions, so applying it for
every thread should be avoided.
This patch fixes the above problem in the following way:
- Modify thread's exit (= __exit_signal()) not to use task_times().
It means {u,s}time in signal struct accumulates raw values instead
of adjusted values. As the result it makes thread_group_cputime()
to return pure sum of "raw" values.
- Introduce a new function thread_group_times(*task, *utime, *stime)
that converts "raw" values of thread_group_cputime() to "adjusted"
values, in same calculation procedure as task_times().
- Modify group's exit (= wait_task_zombie()) to use this introduced
thread_group_times(). It make c{u,s}time in signal struct to
have adjusted values like before this patch.
- Replace some thread_group_cputime() by thread_group_times().
This replacements are only applied where conveys the "adjusted"
cputime to users, and where already uses task_times() near by it.
(i.e. sys_times(), getrusage(), and /proc/<PID>/stat.)
This patch have a positive side effect:
- Before this patch, if a group contains many short-life threads
(e.g. runs 0.9ms and not interrupted by ticks), the group's
cputime could be invisible since thread's cputime was accumulated
after adjusted: imagine adjustment function as adj(ticks, runtime),
{adj(0, 0.9) + adj(0, 0.9) + ....} = {0 + 0 + ....} = 0.
After this patch it will not happen because the adjustment is
applied after accumulated.
v2:
- remove if()s, put new variables into signal_struct.
Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: Spencer Candland <spencer@bluehost.com>
Cc: Americo Wang <xiyou.wangcong@gmail.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: Stanislaw Gruszka <sgruszka@redhat.com>
LKML-Reference: <4B162517.8040909@jp.fujitsu.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-02 16:28:07 +08:00
|
|
|
sig->utime = cputime_add(sig->utime, tsk->utime);
|
|
|
|
|
sig->stime = cputime_add(sig->stime, tsk->stime);
|
2009-11-26 13:49:05 +08:00
|
|
|
sig->gtime = cputime_add(sig->gtime, tsk->gtime);
|
2006-03-29 08:11:18 +08:00
|
|
|
sig->min_flt += tsk->min_flt;
|
|
|
|
|
sig->maj_flt += tsk->maj_flt;
|
|
|
|
|
sig->nvcsw += tsk->nvcsw;
|
|
|
|
|
sig->nivcsw += tsk->nivcsw;
|
2007-05-11 13:22:37 +08:00
|
|
|
sig->inblock += task_io_get_inblock(tsk);
|
|
|
|
|
sig->oublock += task_io_get_oublock(tsk);
|
2008-07-27 23:29:15 +08:00
|
|
|
task_io_accounting_add(&sig->ioac, &tsk->ioac);
|
2009-02-05 19:24:15 +08:00
|
|
|
sig->sum_sched_runtime += tsk->se.sum_exec_runtime;
|
2006-03-29 08:11:18 +08:00
|
|
|
}
|
|
|
|
|
|
2010-05-27 05:43:24 +08:00
|
|
|
sig->nr_threads--;
|
2010-05-27 05:43:19 +08:00
|
|
|
__unhash_process(tsk, group_dead);
|
2006-03-29 08:11:20 +08:00
|
|
|
|
2008-05-24 04:04:41 +08:00
|
|
|
/*
|
|
|
|
|
* Do this under ->siglock, we can race with another thread
|
|
|
|
|
* doing sigqueue_free() if we have SIGQUEUE_PREALLOC signals.
|
|
|
|
|
*/
|
|
|
|
|
flush_sigqueue(&tsk->pending);
|
2006-03-29 08:11:27 +08:00
|
|
|
tsk->sighand = NULL;
|
2006-03-29 08:11:18 +08:00
|
|
|
spin_unlock(&sighand->siglock);
|
|
|
|
|
|
2006-03-29 08:11:27 +08:00
|
|
|
__cleanup_sighand(sighand);
|
2006-03-29 08:11:18 +08:00
|
|
|
clear_tsk_thread_flag(tsk,TIF_SIGPENDING);
|
2010-05-27 05:43:19 +08:00
|
|
|
if (group_dead) {
|
2006-03-29 08:11:18 +08:00
|
|
|
flush_sigqueue(&sig->shared_pending);
|
2010-05-27 05:43:17 +08:00
|
|
|
tty_kref_put(tty);
|
2006-03-29 08:11:18 +08:00
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2006-03-31 18:31:37 +08:00
|
|
|
static void delayed_put_task_struct(struct rcu_head *rhp)
|
|
|
|
|
{
|
tracing, sched: LTTng instrumentation - scheduler
Instrument the scheduler activity (sched_switch, migration, wakeups,
wait for a task, signal delivery) and process/thread
creation/destruction (fork, exit, kthread stop). Actually, kthread
creation is not instrumented in this patch because it is architecture
dependent. It allows to connect tracers such as ftrace which detects
scheduling latencies, good/bad scheduler decisions. Tools like LTTng can
export this scheduler information along with instrumentation of the rest
of the kernel activity to perform post-mortem analysis on the scheduler
activity.
About the performance impact of tracepoints (which is comparable to
markers), even without immediate values optimizations, tests done by
Hideo Aoki on ia64 show no regression. His test case was using hackbench
on a kernel where scheduler instrumentation (about 5 events in code
scheduler code) was added. See the "Tracepoints" patch header for
performance result detail.
Changelog :
- Change instrumentation location and parameter to match ftrace
instrumentation, previously done with kernel markers.
[ mingo@elte.hu: conflict resolutions ]
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
Acked-by: 'Peter Zijlstra' <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-07-19 00:16:17 +08:00
|
|
|
struct task_struct *tsk = container_of(rhp, struct task_struct, rcu);
|
|
|
|
|
|
2010-09-10 03:01:59 +08:00
|
|
|
perf_event_delayed_put(tsk);
|
tracing, sched: LTTng instrumentation - scheduler
Instrument the scheduler activity (sched_switch, migration, wakeups,
wait for a task, signal delivery) and process/thread
creation/destruction (fork, exit, kthread stop). Actually, kthread
creation is not instrumented in this patch because it is architecture
dependent. It allows to connect tracers such as ftrace which detects
scheduling latencies, good/bad scheduler decisions. Tools like LTTng can
export this scheduler information along with instrumentation of the rest
of the kernel activity to perform post-mortem analysis on the scheduler
activity.
About the performance impact of tracepoints (which is comparable to
markers), even without immediate values optimizations, tests done by
Hideo Aoki on ia64 show no regression. His test case was using hackbench
on a kernel where scheduler instrumentation (about 5 events in code
scheduler code) was added. See the "Tracepoints" patch header for
performance result detail.
Changelog :
- Change instrumentation location and parameter to match ftrace
instrumentation, previously done with kernel markers.
[ mingo@elte.hu: conflict resolutions ]
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
Acked-by: 'Peter Zijlstra' <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-07-19 00:16:17 +08:00
|
|
|
trace_sched_process_free(tsk);
|
|
|
|
|
put_task_struct(tsk);
|
2006-03-31 18:31:37 +08:00
|
|
|
}
|
|
|
|
|
|
2008-03-25 09:36:23 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
void release_task(struct task_struct * p)
|
|
|
|
|
{
|
2006-07-03 15:25:41 +08:00
|
|
|
struct task_struct *leader;
|
2005-04-17 06:20:36 +08:00
|
|
|
int zap_leader;
|
2006-03-29 08:11:11 +08:00
|
|
|
repeat:
|
2008-07-26 10:45:48 +08:00
|
|
|
tracehook_prepare_release_task(p);
|
2008-11-14 07:39:19 +08:00
|
|
|
/* don't need to get the RCU readlock here - the process is dead and
|
2010-02-23 09:04:50 +08:00
|
|
|
* can't be modifying its own credentials. But shut RCU-lockdep up */
|
|
|
|
|
rcu_read_lock();
|
2008-11-14 07:39:19 +08:00
|
|
|
atomic_dec(&__task_cred(p)->user->processes);
|
2010-02-23 09:04:50 +08:00
|
|
|
rcu_read_unlock();
|
2008-11-14 07:39:19 +08:00
|
|
|
|
2007-10-19 14:40:03 +08:00
|
|
|
proc_flush_task(p);
|
2009-05-17 17:24:08 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
write_lock_irq(&tasklist_lock);
|
2008-07-26 10:45:48 +08:00
|
|
|
tracehook_finish_release_task(p);
|
2005-04-17 06:20:36 +08:00
|
|
|
__exit_signal(p);
|
2006-03-29 08:11:19 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/*
|
|
|
|
|
* If we are the last non-leader member of the thread
|
|
|
|
|
* group, and the leader is zombie, then notify the
|
|
|
|
|
* group leader's parent process. (if it wants notification.)
|
|
|
|
|
*/
|
|
|
|
|
zap_leader = 0;
|
|
|
|
|
leader = p->group_leader;
|
|
|
|
|
if (leader != p && thread_group_empty(leader) && leader->exit_state == EXIT_ZOMBIE) {
|
2008-04-30 15:53:11 +08:00
|
|
|
BUG_ON(task_detached(leader));
|
2005-04-17 06:20:36 +08:00
|
|
|
do_notify_parent(leader, leader->exit_signal);
|
|
|
|
|
/*
|
|
|
|
|
* If we were the last child thread and the leader has
|
|
|
|
|
* exited already, and the leader's parent ignores SIGCHLD,
|
|
|
|
|
* then we are the one who should release the leader.
|
|
|
|
|
*
|
|
|
|
|
* do_notify_parent() will have marked it self-reaping in
|
|
|
|
|
* that case.
|
|
|
|
|
*/
|
2008-04-30 15:53:11 +08:00
|
|
|
zap_leader = task_detached(leader);
|
2008-07-26 10:45:48 +08:00
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* This maintains the invariant that release_task()
|
|
|
|
|
* only runs on a task in EXIT_DEAD, just for sanity.
|
|
|
|
|
*/
|
|
|
|
|
if (zap_leader)
|
|
|
|
|
leader->exit_state = EXIT_DEAD;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
write_unlock_irq(&tasklist_lock);
|
|
|
|
|
release_thread(p);
|
2006-03-31 18:31:37 +08:00
|
|
|
call_rcu(&p->rcu, delayed_put_task_struct);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
p = leader;
|
|
|
|
|
if (unlikely(zap_leader))
|
|
|
|
|
goto repeat;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* This checks not only the pgrp, but falls back on the pid if no
|
|
|
|
|
* satisfactory pgrp is found. I dunno - gdb doesn't work correctly
|
|
|
|
|
* without this...
|
2007-02-12 16:52:56 +08:00
|
|
|
*
|
|
|
|
|
* The caller must hold rcu lock or the tasklist lock.
|
2005-04-17 06:20:36 +08:00
|
|
|
*/
|
2007-02-12 16:52:56 +08:00
|
|
|
struct pid *session_of_pgrp(struct pid *pgrp)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
|
struct task_struct *p;
|
2007-02-12 16:52:56 +08:00
|
|
|
struct pid *sid = NULL;
|
2006-12-08 18:38:03 +08:00
|
|
|
|
2007-02-12 16:52:56 +08:00
|
|
|
p = pid_task(pgrp, PIDTYPE_PGID);
|
2006-12-08 18:38:03 +08:00
|
|
|
if (p == NULL)
|
2007-02-12 16:52:56 +08:00
|
|
|
p = pid_task(pgrp, PIDTYPE_PID);
|
2006-12-08 18:38:03 +08:00
|
|
|
if (p != NULL)
|
2007-02-12 16:52:56 +08:00
|
|
|
sid = task_session(p);
|
2006-12-08 18:38:03 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
return sid;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Determine if a process group is "orphaned", according to the POSIX
|
|
|
|
|
* definition in 2.2.2.52. Orphaned process groups are not to be affected
|
|
|
|
|
* by terminal-generated stop signals. Newly orphaned process groups are
|
|
|
|
|
* to receive a SIGHUP and a SIGCONT.
|
|
|
|
|
*
|
|
|
|
|
* "I ask you, have you ever known what it is to be an orphan?"
|
|
|
|
|
*/
|
2007-02-12 16:52:57 +08:00
|
|
|
static int will_become_orphaned_pgrp(struct pid *pgrp, struct task_struct *ignored_task)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
|
struct task_struct *p;
|
|
|
|
|
|
2007-02-12 16:52:57 +08:00
|
|
|
do_each_pid_task(pgrp, PIDTYPE_PGID, p) {
|
2008-03-03 02:44:42 +08:00
|
|
|
if ((p == ignored_task) ||
|
|
|
|
|
(p->exit_state && thread_group_empty(p)) ||
|
|
|
|
|
is_global_init(p->real_parent))
|
2005-04-17 06:20:36 +08:00
|
|
|
continue;
|
2008-03-03 02:44:42 +08:00
|
|
|
|
2007-02-12 16:52:57 +08:00
|
|
|
if (task_pgrp(p->real_parent) != pgrp &&
|
2008-03-03 02:44:42 +08:00
|
|
|
task_session(p->real_parent) == task_session(p))
|
|
|
|
|
return 0;
|
2007-02-12 16:52:57 +08:00
|
|
|
} while_each_pid_task(pgrp, PIDTYPE_PGID, p);
|
2008-03-03 02:44:42 +08:00
|
|
|
|
|
|
|
|
return 1;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
2007-02-12 16:52:58 +08:00
|
|
|
int is_current_pgrp_orphaned(void)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
|
int retval;
|
|
|
|
|
|
|
|
|
|
read_lock(&tasklist_lock);
|
2007-02-12 16:52:58 +08:00
|
|
|
retval = will_become_orphaned_pgrp(task_pgrp(current), NULL);
|
2005-04-17 06:20:36 +08:00
|
|
|
read_unlock(&tasklist_lock);
|
|
|
|
|
|
|
|
|
|
return retval;
|
|
|
|
|
}
|
|
|
|
|
|
2007-02-12 16:52:57 +08:00
|
|
|
static int has_stopped_jobs(struct pid *pgrp)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
|
int retval = 0;
|
|
|
|
|
struct task_struct *p;
|
|
|
|
|
|
2007-02-12 16:52:57 +08:00
|
|
|
do_each_pid_task(pgrp, PIDTYPE_PGID, p) {
|
2007-12-07 00:09:35 +08:00
|
|
|
if (!task_is_stopped(p))
|
2005-04-17 06:20:36 +08:00
|
|
|
continue;
|
|
|
|
|
retval = 1;
|
|
|
|
|
break;
|
2007-02-12 16:52:57 +08:00
|
|
|
} while_each_pid_task(pgrp, PIDTYPE_PGID, p);
|
2005-04-17 06:20:36 +08:00
|
|
|
return retval;
|
|
|
|
|
}
|
|
|
|
|
|
2008-03-03 02:44:40 +08:00
|
|
|
/*
|
|
|
|
|
* Check to see if any process groups have become orphaned as
|
|
|
|
|
* a result of our exiting, and if they have any stopped jobs,
|
|
|
|
|
* send them a SIGHUP and then a SIGCONT. (POSIX 3.2.2.2)
|
|
|
|
|
*/
|
|
|
|
|
static void
|
|
|
|
|
kill_orphaned_pgrp(struct task_struct *tsk, struct task_struct *parent)
|
|
|
|
|
{
|
|
|
|
|
struct pid *pgrp = task_pgrp(tsk);
|
|
|
|
|
struct task_struct *ignored_task = tsk;
|
|
|
|
|
|
|
|
|
|
if (!parent)
|
|
|
|
|
/* exit: our father is in a different pgrp than
|
|
|
|
|
* we are and we were the only connection outside.
|
|
|
|
|
*/
|
|
|
|
|
parent = tsk->real_parent;
|
|
|
|
|
else
|
|
|
|
|
/* reparent: our child is in a different pgrp than
|
|
|
|
|
* we are, and it was the only connection outside.
|
|
|
|
|
*/
|
|
|
|
|
ignored_task = NULL;
|
|
|
|
|
|
|
|
|
|
if (task_pgrp(parent) != pgrp &&
|
|
|
|
|
task_session(parent) == task_session(tsk) &&
|
|
|
|
|
will_become_orphaned_pgrp(pgrp, ignored_task) &&
|
|
|
|
|
has_stopped_jobs(pgrp)) {
|
|
|
|
|
__kill_pgrp_info(SIGHUP, SEND_SIG_PRIV, pgrp);
|
|
|
|
|
__kill_pgrp_info(SIGCONT, SEND_SIG_PRIV, pgrp);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/**
|
2007-05-09 17:34:33 +08:00
|
|
|
* reparent_to_kthreadd - Reparent the calling kernel thread to kthreadd
|
2005-04-17 06:20:36 +08:00
|
|
|
*
|
|
|
|
|
* If a kernel thread is launched as a result of a system call, or if
|
2007-05-09 17:34:33 +08:00
|
|
|
* it ever exits, it should generally reparent itself to kthreadd so it
|
|
|
|
|
* isn't in the way of other processes and is correctly cleaned up on exit.
|
2005-04-17 06:20:36 +08:00
|
|
|
*
|
|
|
|
|
* The various task state such as scheduling policy and priority may have
|
|
|
|
|
* been inherited from a user process, so we reset them to sane values here.
|
|
|
|
|
*
|
2007-05-09 17:34:33 +08:00
|
|
|
* NOTE that reparent_to_kthreadd() gives the caller full capabilities.
|
2005-04-17 06:20:36 +08:00
|
|
|
*/
|
2007-05-09 17:34:33 +08:00
|
|
|
static void reparent_to_kthreadd(void)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
|
write_lock_irq(&tasklist_lock);
|
|
|
|
|
|
|
|
|
|
ptrace_unlink(current);
|
|
|
|
|
/* Reparent to init */
|
2007-05-09 17:34:33 +08:00
|
|
|
current->real_parent = current->parent = kthreadd_task;
|
2008-03-25 09:36:23 +08:00
|
|
|
list_move_tail(¤t->sibling, ¤t->real_parent->children);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
/* Set the exit signal to SIGCHLD so we signal init on exit */
|
|
|
|
|
current->exit_signal = SIGCHLD;
|
|
|
|
|
|
2007-07-10 00:51:59 +08:00
|
|
|
if (task_nice(current) < 0)
|
2005-04-17 06:20:36 +08:00
|
|
|
set_user_nice(current, 0);
|
|
|
|
|
/* cpus_allowed? */
|
|
|
|
|
/* rt_priority? */
|
|
|
|
|
/* signals? */
|
|
|
|
|
memcpy(current->signal->rlim, init_task.signal->rlim,
|
|
|
|
|
sizeof(current->signal->rlim));
|
CRED: Inaugurate COW credentials
Inaugurate copy-on-write credentials management. This uses RCU to manage the
credentials pointer in the task_struct with respect to accesses by other tasks.
A process may only modify its own credentials, and so does not need locking to
access or modify its own credentials.
A mutex (cred_replace_mutex) is added to the task_struct to control the effect
of PTRACE_ATTACHED on credential calculations, particularly with respect to
execve().
With this patch, the contents of an active credentials struct may not be
changed directly; rather a new set of credentials must be prepared, modified
and committed using something like the following sequence of events:
struct cred *new = prepare_creds();
int ret = blah(new);
if (ret < 0) {
abort_creds(new);
return ret;
}
return commit_creds(new);
There are some exceptions to this rule: the keyrings pointed to by the active
credentials may be instantiated - keyrings violate the COW rule as managing
COW keyrings is tricky, given that it is possible for a task to directly alter
the keys in a keyring in use by another task.
To help enforce this, various pointers to sets of credentials, such as those in
the task_struct, are declared const. The purpose of this is compile-time
discouragement of altering credentials through those pointers. Once a set of
credentials has been made public through one of these pointers, it may not be
modified, except under special circumstances:
(1) Its reference count may incremented and decremented.
(2) The keyrings to which it points may be modified, but not replaced.
The only safe way to modify anything else is to create a replacement and commit
using the functions described in Documentation/credentials.txt (which will be
added by a later patch).
This patch and the preceding patches have been tested with the LTP SELinux
testsuite.
This patch makes several logical sets of alteration:
(1) execve().
This now prepares and commits credentials in various places in the
security code rather than altering the current creds directly.
(2) Temporary credential overrides.
do_coredump() and sys_faccessat() now prepare their own credentials and
temporarily override the ones currently on the acting thread, whilst
preventing interference from other threads by holding cred_replace_mutex
on the thread being dumped.
This will be replaced in a future patch by something that hands down the
credentials directly to the functions being called, rather than altering
the task's objective credentials.
(3) LSM interface.
A number of functions have been changed, added or removed:
(*) security_capset_check(), ->capset_check()
(*) security_capset_set(), ->capset_set()
Removed in favour of security_capset().
(*) security_capset(), ->capset()
New. This is passed a pointer to the new creds, a pointer to the old
creds and the proposed capability sets. It should fill in the new
creds or return an error. All pointers, barring the pointer to the
new creds, are now const.
(*) security_bprm_apply_creds(), ->bprm_apply_creds()
Changed; now returns a value, which will cause the process to be
killed if it's an error.
(*) security_task_alloc(), ->task_alloc_security()
Removed in favour of security_prepare_creds().
(*) security_cred_free(), ->cred_free()
New. Free security data attached to cred->security.
(*) security_prepare_creds(), ->cred_prepare()
New. Duplicate any security data attached to cred->security.
(*) security_commit_creds(), ->cred_commit()
New. Apply any security effects for the upcoming installation of new
security by commit_creds().
(*) security_task_post_setuid(), ->task_post_setuid()
Removed in favour of security_task_fix_setuid().
(*) security_task_fix_setuid(), ->task_fix_setuid()
Fix up the proposed new credentials for setuid(). This is used by
cap_set_fix_setuid() to implicitly adjust capabilities in line with
setuid() changes. Changes are made to the new credentials, rather
than the task itself as in security_task_post_setuid().
(*) security_task_reparent_to_init(), ->task_reparent_to_init()
Removed. Instead the task being reparented to init is referred
directly to init's credentials.
NOTE! This results in the loss of some state: SELinux's osid no
longer records the sid of the thread that forked it.
(*) security_key_alloc(), ->key_alloc()
(*) security_key_permission(), ->key_permission()
Changed. These now take cred pointers rather than task pointers to
refer to the security context.
(4) sys_capset().
This has been simplified and uses less locking. The LSM functions it
calls have been merged.
(5) reparent_to_kthreadd().
This gives the current thread the same credentials as init by simply using
commit_thread() to point that way.
(6) __sigqueue_alloc() and switch_uid()
__sigqueue_alloc() can't stop the target task from changing its creds
beneath it, so this function gets a reference to the currently applicable
user_struct which it then passes into the sigqueue struct it returns if
successful.
switch_uid() is now called from commit_creds(), and possibly should be
folded into that. commit_creds() should take care of protecting
__sigqueue_alloc().
(7) [sg]et[ug]id() and co and [sg]et_current_groups.
The set functions now all use prepare_creds(), commit_creds() and
abort_creds() to build and check a new set of credentials before applying
it.
security_task_set[ug]id() is called inside the prepared section. This
guarantees that nothing else will affect the creds until we've finished.
The calling of set_dumpable() has been moved into commit_creds().
Much of the functionality of set_user() has been moved into
commit_creds().
The get functions all simply access the data directly.
(8) security_task_prctl() and cap_task_prctl().
security_task_prctl() has been modified to return -ENOSYS if it doesn't
want to handle a function, or otherwise return the return value directly
rather than through an argument.
Additionally, cap_task_prctl() now prepares a new set of credentials, even
if it doesn't end up using it.
(9) Keyrings.
A number of changes have been made to the keyrings code:
(a) switch_uid_keyring(), copy_keys(), exit_keys() and suid_keys() have
all been dropped and built in to the credentials functions directly.
They may want separating out again later.
(b) key_alloc() and search_process_keyrings() now take a cred pointer
rather than a task pointer to specify the security context.
(c) copy_creds() gives a new thread within the same thread group a new
thread keyring if its parent had one, otherwise it discards the thread
keyring.
(d) The authorisation key now points directly to the credentials to extend
the search into rather pointing to the task that carries them.
(e) Installing thread, process or session keyrings causes a new set of
credentials to be created, even though it's not strictly necessary for
process or session keyrings (they're shared).
(10) Usermode helper.
The usermode helper code now carries a cred struct pointer in its
subprocess_info struct instead of a new session keyring pointer. This set
of credentials is derived from init_cred and installed on the new process
after it has been cloned.
call_usermodehelper_setup() allocates the new credentials and
call_usermodehelper_freeinfo() discards them if they haven't been used. A
special cred function (prepare_usermodeinfo_creds()) is provided
specifically for call_usermodehelper_setup() to call.
call_usermodehelper_setkeys() adjusts the credentials to sport the
supplied keyring as the new session keyring.
(11) SELinux.
SELinux has a number of changes, in addition to those to support the LSM
interface changes mentioned above:
(a) selinux_setprocattr() no longer does its check for whether the
current ptracer can access processes with the new SID inside the lock
that covers getting the ptracer's SID. Whilst this lock ensures that
the check is done with the ptracer pinned, the result is only valid
until the lock is released, so there's no point doing it inside the
lock.
(12) is_single_threaded().
This function has been extracted from selinux_setprocattr() and put into
a file of its own in the lib/ directory as join_session_keyring() now
wants to use it too.
The code in SELinux just checked to see whether a task shared mm_structs
with other tasks (CLONE_VM), but that isn't good enough. We really want
to know if they're part of the same thread group (CLONE_THREAD).
(13) nfsd.
The NFS server daemon now has to use the COW credentials to set the
credentials it is going to use. It really needs to pass the credentials
down to the functions it calls, but it can't do that until other patches
in this series have been applied.
Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: James Morris <jmorris@namei.org>
Signed-off-by: James Morris <jmorris@namei.org>
2008-11-14 07:39:23 +08:00
|
|
|
|
|
|
|
|
atomic_inc(&init_cred.usage);
|
|
|
|
|
commit_creds(&init_cred);
|
2005-04-17 06:20:36 +08:00
|
|
|
write_unlock_irq(&tasklist_lock);
|
|
|
|
|
}
|
|
|
|
|
|
2008-02-08 20:19:09 +08:00
|
|
|
void __set_special_pids(struct pid *pid)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2006-01-08 17:03:58 +08:00
|
|
|
struct task_struct *curr = current->group_leader;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2009-10-27 07:49:34 +08:00
|
|
|
if (task_session(curr) != pid)
|
2008-04-30 15:54:27 +08:00
|
|
|
change_pid(curr, PIDTYPE_SID, pid);
|
2009-04-03 07:58:39 +08:00
|
|
|
|
|
|
|
|
if (task_pgrp(curr) != pid)
|
2008-04-30 15:54:27 +08:00
|
|
|
change_pid(curr, PIDTYPE_PGID, pid);
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
2008-02-08 20:19:09 +08:00
|
|
|
static void set_special_pids(struct pid *pid)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
|
write_lock_irq(&tasklist_lock);
|
2008-02-08 20:19:09 +08:00
|
|
|
__set_special_pids(pid);
|
2005-04-17 06:20:36 +08:00
|
|
|
write_unlock_irq(&tasklist_lock);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
2009-06-18 07:27:23 +08:00
|
|
|
* Let kernel threads use this to say that they allow a certain signal.
|
|
|
|
|
* Must not be used if kthread was cloned with CLONE_SIGHAND.
|
2005-04-17 06:20:36 +08:00
|
|
|
*/
|
|
|
|
|
int allow_signal(int sig)
|
|
|
|
|
{
|
2005-05-01 23:59:14 +08:00
|
|
|
if (!valid_signal(sig) || sig < 1)
|
2005-04-17 06:20:36 +08:00
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
|
|
spin_lock_irq(¤t->sighand->siglock);
|
2009-06-18 07:27:23 +08:00
|
|
|
/* This is only needed for daemonize()'ed kthreads */
|
2005-04-17 06:20:36 +08:00
|
|
|
sigdelset(¤t->blocked, sig);
|
2009-06-18 07:27:23 +08:00
|
|
|
/*
|
|
|
|
|
* Kernel threads handle their own signals. Let the signal code
|
|
|
|
|
* know it'll be handled, so that they don't get converted to
|
|
|
|
|
* SIGKILL or just silently dropped.
|
|
|
|
|
*/
|
|
|
|
|
current->sighand->action[(sig)-1].sa.sa_handler = (void __user *)2;
|
2005-04-17 06:20:36 +08:00
|
|
|
recalc_sigpending();
|
|
|
|
|
spin_unlock_irq(¤t->sighand->siglock);
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
EXPORT_SYMBOL(allow_signal);
|
|
|
|
|
|
|
|
|
|
int disallow_signal(int sig)
|
|
|
|
|
{
|
2005-05-01 23:59:14 +08:00
|
|
|
if (!valid_signal(sig) || sig < 1)
|
2005-04-17 06:20:36 +08:00
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
|
|
spin_lock_irq(¤t->sighand->siglock);
|
2007-05-09 17:34:37 +08:00
|
|
|
current->sighand->action[(sig)-1].sa.sa_handler = SIG_IGN;
|
2005-04-17 06:20:36 +08:00
|
|
|
recalc_sigpending();
|
|
|
|
|
spin_unlock_irq(¤t->sighand->siglock);
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
EXPORT_SYMBOL(disallow_signal);
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Put all the gunge required to become a kernel thread without
|
|
|
|
|
* attached user resources in one place where it belongs.
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
void daemonize(const char *name, ...)
|
|
|
|
|
{
|
|
|
|
|
va_list args;
|
|
|
|
|
sigset_t blocked;
|
|
|
|
|
|
|
|
|
|
va_start(args, name);
|
|
|
|
|
vsnprintf(current->comm, sizeof(current->comm), name, args);
|
|
|
|
|
va_end(args);
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* If we were started as result of loading a module, close all of the
|
|
|
|
|
* user space pages. We don't need them, and if we didn't close them
|
|
|
|
|
* they would be locked into memory.
|
|
|
|
|
*/
|
|
|
|
|
exit_mm(current);
|
2007-07-17 19:03:35 +08:00
|
|
|
/*
|
|
|
|
|
* We don't want to have TIF_FREEZE set if the system-wide hibernation
|
|
|
|
|
* or suspend transition begins right now.
|
|
|
|
|
*/
|
2008-07-25 16:47:37 +08:00
|
|
|
current->flags |= (PF_NOFREEZE | PF_KTHREAD);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2008-02-08 20:19:09 +08:00
|
|
|
if (current->nsproxy != &init_nsproxy) {
|
|
|
|
|
get_nsproxy(&init_nsproxy);
|
|
|
|
|
switch_task_namespaces(current, &init_nsproxy);
|
|
|
|
|
}
|
2008-02-08 20:19:10 +08:00
|
|
|
set_special_pids(&init_struct_pid);
|
2006-12-08 18:36:04 +08:00
|
|
|
proc_clear_tty(current);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
/* Block and flush all signals */
|
|
|
|
|
sigfillset(&blocked);
|
|
|
|
|
sigprocmask(SIG_BLOCK, &blocked, NULL);
|
|
|
|
|
flush_signals(current);
|
|
|
|
|
|
|
|
|
|
/* Become as one with the init task */
|
|
|
|
|
|
2009-03-30 07:00:13 +08:00
|
|
|
daemonize_fs_struct();
|
2007-10-19 14:39:59 +08:00
|
|
|
exit_files(current);
|
2005-04-17 06:20:36 +08:00
|
|
|
current->files = init_task.files;
|
|
|
|
|
atomic_inc(¤t->files->count);
|
|
|
|
|
|
2007-05-09 17:34:33 +08:00
|
|
|
reparent_to_kthreadd();
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
EXPORT_SYMBOL(daemonize);
|
|
|
|
|
|
2006-01-15 05:20:43 +08:00
|
|
|
static void close_files(struct files_struct * files)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
|
int i, j;
|
2005-09-10 04:04:10 +08:00
|
|
|
struct fdtable *fdt;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
j = 0;
|
2005-09-17 10:28:13 +08:00
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* It is safe to dereference the fd table without RCU or
|
|
|
|
|
* ->file_lock because this is the last reference to the
|
2010-02-23 09:04:50 +08:00
|
|
|
* files structure. But use RCU to shut RCU-lockdep up.
|
2005-09-17 10:28:13 +08:00
|
|
|
*/
|
2010-02-23 09:04:50 +08:00
|
|
|
rcu_read_lock();
|
2005-09-10 04:04:10 +08:00
|
|
|
fdt = files_fdtable(files);
|
2010-02-23 09:04:50 +08:00
|
|
|
rcu_read_unlock();
|
2005-04-17 06:20:36 +08:00
|
|
|
for (;;) {
|
|
|
|
|
unsigned long set;
|
|
|
|
|
i = j * __NFDBITS;
|
2006-12-10 18:21:12 +08:00
|
|
|
if (i >= fdt->max_fds)
|
2005-04-17 06:20:36 +08:00
|
|
|
break;
|
2005-09-10 04:04:10 +08:00
|
|
|
set = fdt->open_fds->fds_bits[j++];
|
2005-04-17 06:20:36 +08:00
|
|
|
while (set) {
|
|
|
|
|
if (set & 1) {
|
2005-09-10 04:04:10 +08:00
|
|
|
struct file * file = xchg(&fdt->fd[i], NULL);
|
2007-02-12 16:52:26 +08:00
|
|
|
if (file) {
|
2005-04-17 06:20:36 +08:00
|
|
|
filp_close(file, files);
|
2007-02-12 16:52:26 +08:00
|
|
|
cond_resched();
|
|
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
i++;
|
|
|
|
|
set >>= 1;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
struct files_struct *get_files_struct(struct task_struct *task)
|
|
|
|
|
{
|
|
|
|
|
struct files_struct *files;
|
|
|
|
|
|
|
|
|
|
task_lock(task);
|
|
|
|
|
files = task->files;
|
|
|
|
|
if (files)
|
|
|
|
|
atomic_inc(&files->count);
|
|
|
|
|
task_unlock(task);
|
|
|
|
|
|
|
|
|
|
return files;
|
|
|
|
|
}
|
|
|
|
|
|
2008-02-08 20:19:53 +08:00
|
|
|
void put_files_struct(struct files_struct *files)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2005-09-10 04:04:10 +08:00
|
|
|
struct fdtable *fdt;
|
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
if (atomic_dec_and_test(&files->count)) {
|
|
|
|
|
close_files(files);
|
|
|
|
|
/*
|
|
|
|
|
* Free the fd and fdset arrays if we expanded them.
|
2005-09-10 04:04:13 +08:00
|
|
|
* If the fdtable was embedded, pass files for freeing
|
|
|
|
|
* at the end of the RCU grace period. Otherwise,
|
|
|
|
|
* you can free files immediately.
|
2005-04-17 06:20:36 +08:00
|
|
|
*/
|
2010-02-23 09:04:50 +08:00
|
|
|
rcu_read_lock();
|
2005-09-10 04:04:10 +08:00
|
|
|
fdt = files_fdtable(files);
|
2006-12-10 18:21:17 +08:00
|
|
|
if (fdt != &files->fdtab)
|
2005-09-10 04:04:13 +08:00
|
|
|
kmem_cache_free(files_cachep, files);
|
2006-12-22 17:10:43 +08:00
|
|
|
free_fdtable(fdt);
|
2010-02-23 09:04:50 +08:00
|
|
|
rcu_read_unlock();
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2008-04-22 17:31:30 +08:00
|
|
|
void reset_files_struct(struct files_struct *files)
|
2006-09-29 17:00:05 +08:00
|
|
|
{
|
2008-04-22 17:31:30 +08:00
|
|
|
struct task_struct *tsk = current;
|
2006-09-29 17:00:05 +08:00
|
|
|
struct files_struct *old;
|
|
|
|
|
|
|
|
|
|
old = tsk->files;
|
|
|
|
|
task_lock(tsk);
|
|
|
|
|
tsk->files = files;
|
|
|
|
|
task_unlock(tsk);
|
|
|
|
|
put_files_struct(old);
|
|
|
|
|
}
|
|
|
|
|
|
2008-04-22 17:35:42 +08:00
|
|
|
void exit_files(struct task_struct *tsk)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
|
struct files_struct * files = tsk->files;
|
|
|
|
|
|
|
|
|
|
if (files) {
|
|
|
|
|
task_lock(tsk);
|
|
|
|
|
tsk->files = NULL;
|
|
|
|
|
task_unlock(tsk);
|
|
|
|
|
put_files_struct(files);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
cgroups: add an owner to the mm_struct
Remove the mem_cgroup member from mm_struct and instead adds an owner.
This approach was suggested by Paul Menage. The advantage of this approach
is that, once the mm->owner is known, using the subsystem id, the cgroup
can be determined. It also allows several control groups that are
virtually grouped by mm_struct, to exist independent of the memory
controller i.e., without adding mem_cgroup's for each controller, to
mm_struct.
A new config option CONFIG_MM_OWNER is added and the memory resource
controller selects this config option.
This patch also adds cgroup callbacks to notify subsystems when mm->owner
changes. The mm_cgroup_changed callback is called with the task_lock() of
the new task held and is called just prior to changing the mm->owner.
I am indebted to Paul Menage for the several reviews of this patchset and
helping me make it lighter and simpler.
This patch was tested on a powerpc box, it was compiled with both the
MM_OWNER config turned on and off.
After the thread group leader exits, it's moved to init_css_state by
cgroup_exit(), thus all future charges from runnings threads would be
redirected to the init_css_set's subsystem.
Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Cc: Pavel Emelianov <xemul@openvz.org>
Cc: Hugh Dickins <hugh@veritas.com>
Cc: Sudhir Kumar <skumar@linux.vnet.ibm.com>
Cc: YAMAMOTO Takashi <yamamoto@valinux.co.jp>
Cc: Hirokazu Takahashi <taka@valinux.co.jp>
Cc: David Rientjes <rientjes@google.com>,
Cc: Balbir Singh <balbir@linux.vnet.ibm.com>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Acked-by: Pekka Enberg <penberg@cs.helsinki.fi>
Reviewed-by: Paul Menage <menage@google.com>
Cc: Oleg Nesterov <oleg@tv-sign.ru>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-29 16:00:16 +08:00
|
|
|
#ifdef CONFIG_MM_OWNER
|
|
|
|
|
/*
|
|
|
|
|
* Task p is exiting and it owned mm, lets find a new owner for it
|
|
|
|
|
*/
|
|
|
|
|
static inline int
|
|
|
|
|
mm_need_new_owner(struct mm_struct *mm, struct task_struct *p)
|
|
|
|
|
{
|
|
|
|
|
/*
|
|
|
|
|
* If there are other users of the mm and the owner (us) is exiting
|
|
|
|
|
* we need to find a new owner to take on the responsibility.
|
|
|
|
|
*/
|
|
|
|
|
if (atomic_read(&mm->mm_users) <= 1)
|
|
|
|
|
return 0;
|
|
|
|
|
if (mm->owner != p)
|
|
|
|
|
return 0;
|
|
|
|
|
return 1;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
void mm_update_next_owner(struct mm_struct *mm)
|
|
|
|
|
{
|
|
|
|
|
struct task_struct *c, *g, *p = current;
|
|
|
|
|
|
|
|
|
|
retry:
|
|
|
|
|
if (!mm_need_new_owner(mm, p))
|
|
|
|
|
return;
|
|
|
|
|
|
|
|
|
|
read_lock(&tasklist_lock);
|
|
|
|
|
/*
|
|
|
|
|
* Search in the children
|
|
|
|
|
*/
|
|
|
|
|
list_for_each_entry(c, &p->children, sibling) {
|
|
|
|
|
if (c->mm == mm)
|
|
|
|
|
goto assign_new_owner;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Search in the siblings
|
|
|
|
|
*/
|
2009-06-18 07:27:29 +08:00
|
|
|
list_for_each_entry(c, &p->real_parent->children, sibling) {
|
cgroups: add an owner to the mm_struct
Remove the mem_cgroup member from mm_struct and instead adds an owner.
This approach was suggested by Paul Menage. The advantage of this approach
is that, once the mm->owner is known, using the subsystem id, the cgroup
can be determined. It also allows several control groups that are
virtually grouped by mm_struct, to exist independent of the memory
controller i.e., without adding mem_cgroup's for each controller, to
mm_struct.
A new config option CONFIG_MM_OWNER is added and the memory resource
controller selects this config option.
This patch also adds cgroup callbacks to notify subsystems when mm->owner
changes. The mm_cgroup_changed callback is called with the task_lock() of
the new task held and is called just prior to changing the mm->owner.
I am indebted to Paul Menage for the several reviews of this patchset and
helping me make it lighter and simpler.
This patch was tested on a powerpc box, it was compiled with both the
MM_OWNER config turned on and off.
After the thread group leader exits, it's moved to init_css_state by
cgroup_exit(), thus all future charges from runnings threads would be
redirected to the init_css_set's subsystem.
Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Cc: Pavel Emelianov <xemul@openvz.org>
Cc: Hugh Dickins <hugh@veritas.com>
Cc: Sudhir Kumar <skumar@linux.vnet.ibm.com>
Cc: YAMAMOTO Takashi <yamamoto@valinux.co.jp>
Cc: Hirokazu Takahashi <taka@valinux.co.jp>
Cc: David Rientjes <rientjes@google.com>,
Cc: Balbir Singh <balbir@linux.vnet.ibm.com>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Acked-by: Pekka Enberg <penberg@cs.helsinki.fi>
Reviewed-by: Paul Menage <menage@google.com>
Cc: Oleg Nesterov <oleg@tv-sign.ru>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-29 16:00:16 +08:00
|
|
|
if (c->mm == mm)
|
|
|
|
|
goto assign_new_owner;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Search through everything else. We should not get
|
|
|
|
|
* here often
|
|
|
|
|
*/
|
|
|
|
|
do_each_thread(g, c) {
|
|
|
|
|
if (c->mm == mm)
|
|
|
|
|
goto assign_new_owner;
|
|
|
|
|
} while_each_thread(g, c);
|
|
|
|
|
|
|
|
|
|
read_unlock(&tasklist_lock);
|
mm owner: fix race between swapoff and exit
There's a race between mm->owner assignment and swapoff, more easily
seen when task slab poisoning is turned on. The condition occurs when
try_to_unuse() runs in parallel with an exiting task. A similar race
can occur with callers of get_task_mm(), such as /proc/<pid>/<mmstats>
or ptrace or page migration.
CPU0 CPU1
try_to_unuse
looks at mm = task0->mm
increments mm->mm_users
task 0 exits
mm->owner needs to be updated, but no
new owner is found (mm_users > 1, but
no other task has task->mm = task0->mm)
mm_update_next_owner() leaves
mmput(mm) decrements mm->mm_users
task0 freed
dereferencing mm->owner fails
The fix is to notify the subsystem via mm_owner_changed callback(),
if no new owner is found, by specifying the new task as NULL.
Jiri Slaby:
mm->owner was set to NULL prior to calling cgroup_mm_owner_callbacks(), but
must be set after that, so as not to pass NULL as old owner causing oops.
Daisuke Nishimura:
mm_update_next_owner() may set mm->owner to NULL, but mem_cgroup_from_task()
and its callers need to take account of this situation to avoid oops.
Hugh Dickins:
Lockdep warning and hang below exec_mmap() when testing these patches.
exit_mm() up_reads mmap_sem before calling mm_update_next_owner(),
so exec_mmap() now needs to do the same. And with that repositioning,
there's now no point in mm_need_new_owner() allowing for NULL mm.
Reported-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Signed-off-by: Jiri Slaby <jirislaby@gmail.com>
Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Paul Menage <menage@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-09-29 06:09:31 +08:00
|
|
|
/*
|
|
|
|
|
* We found no owner yet mm_users > 1: this implies that we are
|
|
|
|
|
* most likely racing with swapoff (try_to_unuse()) or /proc or
|
2009-01-07 06:39:22 +08:00
|
|
|
* ptrace or page migration (get_task_mm()). Mark owner as NULL.
|
mm owner: fix race between swapoff and exit
There's a race between mm->owner assignment and swapoff, more easily
seen when task slab poisoning is turned on. The condition occurs when
try_to_unuse() runs in parallel with an exiting task. A similar race
can occur with callers of get_task_mm(), such as /proc/<pid>/<mmstats>
or ptrace or page migration.
CPU0 CPU1
try_to_unuse
looks at mm = task0->mm
increments mm->mm_users
task 0 exits
mm->owner needs to be updated, but no
new owner is found (mm_users > 1, but
no other task has task->mm = task0->mm)
mm_update_next_owner() leaves
mmput(mm) decrements mm->mm_users
task0 freed
dereferencing mm->owner fails
The fix is to notify the subsystem via mm_owner_changed callback(),
if no new owner is found, by specifying the new task as NULL.
Jiri Slaby:
mm->owner was set to NULL prior to calling cgroup_mm_owner_callbacks(), but
must be set after that, so as not to pass NULL as old owner causing oops.
Daisuke Nishimura:
mm_update_next_owner() may set mm->owner to NULL, but mem_cgroup_from_task()
and its callers need to take account of this situation to avoid oops.
Hugh Dickins:
Lockdep warning and hang below exec_mmap() when testing these patches.
exit_mm() up_reads mmap_sem before calling mm_update_next_owner(),
so exec_mmap() now needs to do the same. And with that repositioning,
there's now no point in mm_need_new_owner() allowing for NULL mm.
Reported-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Signed-off-by: Jiri Slaby <jirislaby@gmail.com>
Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Paul Menage <menage@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-09-29 06:09:31 +08:00
|
|
|
*/
|
|
|
|
|
mm->owner = NULL;
|
cgroups: add an owner to the mm_struct
Remove the mem_cgroup member from mm_struct and instead adds an owner.
This approach was suggested by Paul Menage. The advantage of this approach
is that, once the mm->owner is known, using the subsystem id, the cgroup
can be determined. It also allows several control groups that are
virtually grouped by mm_struct, to exist independent of the memory
controller i.e., without adding mem_cgroup's for each controller, to
mm_struct.
A new config option CONFIG_MM_OWNER is added and the memory resource
controller selects this config option.
This patch also adds cgroup callbacks to notify subsystems when mm->owner
changes. The mm_cgroup_changed callback is called with the task_lock() of
the new task held and is called just prior to changing the mm->owner.
I am indebted to Paul Menage for the several reviews of this patchset and
helping me make it lighter and simpler.
This patch was tested on a powerpc box, it was compiled with both the
MM_OWNER config turned on and off.
After the thread group leader exits, it's moved to init_css_state by
cgroup_exit(), thus all future charges from runnings threads would be
redirected to the init_css_set's subsystem.
Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Cc: Pavel Emelianov <xemul@openvz.org>
Cc: Hugh Dickins <hugh@veritas.com>
Cc: Sudhir Kumar <skumar@linux.vnet.ibm.com>
Cc: YAMAMOTO Takashi <yamamoto@valinux.co.jp>
Cc: Hirokazu Takahashi <taka@valinux.co.jp>
Cc: David Rientjes <rientjes@google.com>,
Cc: Balbir Singh <balbir@linux.vnet.ibm.com>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Acked-by: Pekka Enberg <penberg@cs.helsinki.fi>
Reviewed-by: Paul Menage <menage@google.com>
Cc: Oleg Nesterov <oleg@tv-sign.ru>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-29 16:00:16 +08:00
|
|
|
return;
|
|
|
|
|
|
|
|
|
|
assign_new_owner:
|
|
|
|
|
BUG_ON(c == p);
|
|
|
|
|
get_task_struct(c);
|
|
|
|
|
/*
|
|
|
|
|
* The task_lock protects c->mm from changing.
|
|
|
|
|
* We always want mm->owner->mm == mm
|
|
|
|
|
*/
|
|
|
|
|
task_lock(c);
|
2009-01-07 06:39:22 +08:00
|
|
|
/*
|
|
|
|
|
* Delay read_unlock() till we have the task_lock()
|
|
|
|
|
* to ensure that c does not slip away underneath us
|
|
|
|
|
*/
|
|
|
|
|
read_unlock(&tasklist_lock);
|
cgroups: add an owner to the mm_struct
Remove the mem_cgroup member from mm_struct and instead adds an owner.
This approach was suggested by Paul Menage. The advantage of this approach
is that, once the mm->owner is known, using the subsystem id, the cgroup
can be determined. It also allows several control groups that are
virtually grouped by mm_struct, to exist independent of the memory
controller i.e., without adding mem_cgroup's for each controller, to
mm_struct.
A new config option CONFIG_MM_OWNER is added and the memory resource
controller selects this config option.
This patch also adds cgroup callbacks to notify subsystems when mm->owner
changes. The mm_cgroup_changed callback is called with the task_lock() of
the new task held and is called just prior to changing the mm->owner.
I am indebted to Paul Menage for the several reviews of this patchset and
helping me make it lighter and simpler.
This patch was tested on a powerpc box, it was compiled with both the
MM_OWNER config turned on and off.
After the thread group leader exits, it's moved to init_css_state by
cgroup_exit(), thus all future charges from runnings threads would be
redirected to the init_css_set's subsystem.
Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Cc: Pavel Emelianov <xemul@openvz.org>
Cc: Hugh Dickins <hugh@veritas.com>
Cc: Sudhir Kumar <skumar@linux.vnet.ibm.com>
Cc: YAMAMOTO Takashi <yamamoto@valinux.co.jp>
Cc: Hirokazu Takahashi <taka@valinux.co.jp>
Cc: David Rientjes <rientjes@google.com>,
Cc: Balbir Singh <balbir@linux.vnet.ibm.com>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Acked-by: Pekka Enberg <penberg@cs.helsinki.fi>
Reviewed-by: Paul Menage <menage@google.com>
Cc: Oleg Nesterov <oleg@tv-sign.ru>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-29 16:00:16 +08:00
|
|
|
if (c->mm != mm) {
|
|
|
|
|
task_unlock(c);
|
|
|
|
|
put_task_struct(c);
|
|
|
|
|
goto retry;
|
|
|
|
|
}
|
|
|
|
|
mm->owner = c;
|
|
|
|
|
task_unlock(c);
|
|
|
|
|
put_task_struct(c);
|
|
|
|
|
}
|
|
|
|
|
#endif /* CONFIG_MM_OWNER */
|
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/*
|
|
|
|
|
* Turn us into a lazy TLB process if we
|
|
|
|
|
* aren't already..
|
|
|
|
|
*/
|
2005-05-01 23:59:29 +08:00
|
|
|
static void exit_mm(struct task_struct * tsk)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
|
struct mm_struct *mm = tsk->mm;
|
2008-07-25 16:47:44 +08:00
|
|
|
struct core_state *core_state;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
mm_release(tsk, mm);
|
|
|
|
|
if (!mm)
|
|
|
|
|
return;
|
|
|
|
|
/*
|
|
|
|
|
* Serialize with any possible pending coredump.
|
2008-07-25 16:47:41 +08:00
|
|
|
* We must hold mmap_sem around checking core_state
|
2005-04-17 06:20:36 +08:00
|
|
|
* and clearing tsk->mm. The core-inducing thread
|
2008-07-25 16:47:41 +08:00
|
|
|
* will increment ->nr_threads for each thread in the
|
2005-04-17 06:20:36 +08:00
|
|
|
* group with ->mm != NULL.
|
|
|
|
|
*/
|
|
|
|
|
down_read(&mm->mmap_sem);
|
2008-07-25 16:47:44 +08:00
|
|
|
core_state = mm->core_state;
|
|
|
|
|
if (core_state) {
|
|
|
|
|
struct core_thread self;
|
2005-04-17 06:20:36 +08:00
|
|
|
up_read(&mm->mmap_sem);
|
|
|
|
|
|
2008-07-25 16:47:44 +08:00
|
|
|
self.task = tsk;
|
|
|
|
|
self.next = xchg(&core_state->dumper.next, &self);
|
|
|
|
|
/*
|
|
|
|
|
* Implies mb(), the result of xchg() must be visible
|
|
|
|
|
* to core_state->dumper.
|
|
|
|
|
*/
|
|
|
|
|
if (atomic_dec_and_test(&core_state->nr_threads))
|
|
|
|
|
complete(&core_state->startup);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2008-07-25 16:47:46 +08:00
|
|
|
for (;;) {
|
|
|
|
|
set_task_state(tsk, TASK_UNINTERRUPTIBLE);
|
|
|
|
|
if (!self.task) /* see coredump_finish() */
|
|
|
|
|
break;
|
|
|
|
|
schedule();
|
|
|
|
|
}
|
|
|
|
|
__set_task_state(tsk, TASK_RUNNING);
|
2005-04-17 06:20:36 +08:00
|
|
|
down_read(&mm->mmap_sem);
|
|
|
|
|
}
|
|
|
|
|
atomic_inc(&mm->mm_count);
|
2006-06-23 17:06:06 +08:00
|
|
|
BUG_ON(mm != tsk->active_mm);
|
2005-04-17 06:20:36 +08:00
|
|
|
/* more a memory barrier than a real lock */
|
|
|
|
|
task_lock(tsk);
|
|
|
|
|
tsk->mm = NULL;
|
|
|
|
|
up_read(&mm->mmap_sem);
|
|
|
|
|
enter_lazy_tlb(mm, current);
|
2007-07-19 16:47:33 +08:00
|
|
|
/* We don't want this task to be frozen prematurely */
|
|
|
|
|
clear_freeze_flag(tsk);
|
2010-10-27 05:21:23 +08:00
|
|
|
if (tsk->signal->oom_score_adj == OOM_SCORE_ADJ_MIN)
|
|
|
|
|
atomic_dec(&mm->oom_disable_count);
|
2005-04-17 06:20:36 +08:00
|
|
|
task_unlock(tsk);
|
cgroups: add an owner to the mm_struct
Remove the mem_cgroup member from mm_struct and instead adds an owner.
This approach was suggested by Paul Menage. The advantage of this approach
is that, once the mm->owner is known, using the subsystem id, the cgroup
can be determined. It also allows several control groups that are
virtually grouped by mm_struct, to exist independent of the memory
controller i.e., without adding mem_cgroup's for each controller, to
mm_struct.
A new config option CONFIG_MM_OWNER is added and the memory resource
controller selects this config option.
This patch also adds cgroup callbacks to notify subsystems when mm->owner
changes. The mm_cgroup_changed callback is called with the task_lock() of
the new task held and is called just prior to changing the mm->owner.
I am indebted to Paul Menage for the several reviews of this patchset and
helping me make it lighter and simpler.
This patch was tested on a powerpc box, it was compiled with both the
MM_OWNER config turned on and off.
After the thread group leader exits, it's moved to init_css_state by
cgroup_exit(), thus all future charges from runnings threads would be
redirected to the init_css_set's subsystem.
Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Cc: Pavel Emelianov <xemul@openvz.org>
Cc: Hugh Dickins <hugh@veritas.com>
Cc: Sudhir Kumar <skumar@linux.vnet.ibm.com>
Cc: YAMAMOTO Takashi <yamamoto@valinux.co.jp>
Cc: Hirokazu Takahashi <taka@valinux.co.jp>
Cc: David Rientjes <rientjes@google.com>,
Cc: Balbir Singh <balbir@linux.vnet.ibm.com>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Acked-by: Pekka Enberg <penberg@cs.helsinki.fi>
Reviewed-by: Paul Menage <menage@google.com>
Cc: Oleg Nesterov <oleg@tv-sign.ru>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-29 16:00:16 +08:00
|
|
|
mm_update_next_owner(mm);
|
2005-04-17 06:20:36 +08:00
|
|
|
mmput(mm);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* When we die, we re-parent all our children.
|
|
|
|
|
* Try to give them to another thread in our thread
|
|
|
|
|
* group, and if no such member exists, give it to
|
2006-12-08 18:38:01 +08:00
|
|
|
* the child reaper process (ie "init") in our pid
|
|
|
|
|
* space.
|
2005-04-17 06:20:36 +08:00
|
|
|
*/
|
2008-09-03 05:35:49 +08:00
|
|
|
static struct task_struct *find_new_reaper(struct task_struct *father)
|
2010-10-28 06:34:10 +08:00
|
|
|
__releases(&tasklist_lock)
|
|
|
|
|
__acquires(&tasklist_lock)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2008-09-03 05:35:49 +08:00
|
|
|
struct pid_namespace *pid_ns = task_active_pid_ns(father);
|
|
|
|
|
struct task_struct *thread;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2008-09-03 05:35:49 +08:00
|
|
|
thread = father;
|
|
|
|
|
while_each_thread(father, thread) {
|
|
|
|
|
if (thread->flags & PF_EXITING)
|
|
|
|
|
continue;
|
|
|
|
|
if (unlikely(pid_ns->child_reaper == father))
|
|
|
|
|
pid_ns->child_reaper = thread;
|
|
|
|
|
return thread;
|
|
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2008-09-03 05:35:49 +08:00
|
|
|
if (unlikely(pid_ns->child_reaper == father)) {
|
|
|
|
|
write_unlock_irq(&tasklist_lock);
|
|
|
|
|
if (unlikely(pid_ns == &init_pid_ns))
|
|
|
|
|
panic("Attempted to kill init!");
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2008-09-03 05:35:49 +08:00
|
|
|
zap_pid_ns_processes(pid_ns);
|
|
|
|
|
write_lock_irq(&tasklist_lock);
|
2005-04-17 06:20:36 +08:00
|
|
|
/*
|
2008-09-03 05:35:49 +08:00
|
|
|
* We can not clear ->child_reaper or leave it alone.
|
|
|
|
|
* There may by stealth EXIT_DEAD tasks on ->children,
|
|
|
|
|
* forget_original_parent() must move them somewhere.
|
2005-04-17 06:20:36 +08:00
|
|
|
*/
|
2008-09-03 05:35:49 +08:00
|
|
|
pid_ns->child_reaper = init_pid_ns.child_reaper;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
pid namespaces: rework forget_original_parent()
A pid namespace is a "view" of a particular set of tasks on the system. They
work in a similar way to filesystem namespaces. A file (or a process) can be
accessed in multiple namespaces, but it may have a different name in each. In
a filesystem, this name might be /etc/passwd in one namespace, but
/chroot/etc/passwd in another.
For processes, a process may have pid 1234 in one namespace, but be pid 1 in
another. This allows new pid namespaces to have basically arbitrary pids, and
not have to worry about what pids exist in other namespaces. This is
essential for checkpoint/restart where a restarted process's pid might collide
with an existing process on the system's pid.
In this particular implementation, pid namespaces have a parent-child
relationship, just like processes. A process in a pid namespace may see all
of the processes in the same namespace, as well as all of the processes in all
of the namespaces which are children of its namespace. Processes may not,
however, see others which are in their parent's namespace, but not in their
own. The same goes for sibling namespaces.
The know issue to be solved in the nearest future is signal handling in the
namespace boundary. That is, currently the namespace's init is treated like
an ordinary task that can be killed from within an namespace. Ideally, the
signal handling by the namespace's init should have two sides: when signaling
the init from its namespace, the init should look like a real init task, i.e.
receive only those signals, that is explicitly wants to; when signaling the
init from one of the parent namespaces, init should look like an ordinary
task, i.e. receive any signal, only taking the general permissions into
account.
The pid namespace was developed by Pavel Emlyanov and Sukadev Bhattiprolu and
we eventually came to almost the same implementation, which differed in some
details. This set is based on Pavel's patches, but it includes comments and
patches that from Sukadev.
Many thanks to Oleg, who reviewed the patches, pointed out many BUGs and made
valuable advises on how to make this set cleaner.
This patch:
We have to call exit_task_namespaces() only after the exiting task has
reparented all his children and is sure that no other threads will reparent
theirs for it. Why this is needed is explained in appropriate patch. This
one only reworks the forget_original_parent() so that after calling this a
task cannot be/become parent of any other task.
We check PF_EXITING instead of ->exit_state while choosing the new parent.
Note that tasklits_lock acts as a barrier, everyone who takes tasklist after
us (when forget_original_parent() drops it) must see PF_EXITING.
The other changes are just cleanups. They just move some code from
exit_notify to forget_original_parent(). It is a bit silly to declare
ptrace_dead in exit_notify(), take tasklist, pass ptrace_dead to
forget_original_parent(), unlock-lock-unlock tasklist, and then use
ptrace_dead.
Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru>
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Cc: Sukadev Bhattiprolu <sukadev@us.ibm.com>
Cc: Paul Menage <menage@google.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-19 14:40:00 +08:00
|
|
|
|
2008-09-03 05:35:49 +08:00
|
|
|
return pid_ns->child_reaper;
|
|
|
|
|
}
|
|
|
|
|
|
2009-04-03 07:58:19 +08:00
|
|
|
/*
|
|
|
|
|
* Any that need to be release_task'd are put on the @dead list.
|
|
|
|
|
*/
|
2009-12-18 07:27:15 +08:00
|
|
|
static void reparent_leader(struct task_struct *father, struct task_struct *p,
|
2009-04-03 07:58:19 +08:00
|
|
|
struct list_head *dead)
|
|
|
|
|
{
|
|
|
|
|
list_move_tail(&p->sibling, &p->real_parent->children);
|
|
|
|
|
|
|
|
|
|
if (task_detached(p))
|
|
|
|
|
return;
|
|
|
|
|
/*
|
|
|
|
|
* If this is a threaded reparent there is no need to
|
|
|
|
|
* notify anyone anything has happened.
|
|
|
|
|
*/
|
|
|
|
|
if (same_thread_group(p->real_parent, father))
|
|
|
|
|
return;
|
|
|
|
|
|
|
|
|
|
/* We don't want people slaying init. */
|
|
|
|
|
p->exit_signal = SIGCHLD;
|
|
|
|
|
|
|
|
|
|
/* If it has exited notify the new parent about this child's death. */
|
2009-06-18 07:27:30 +08:00
|
|
|
if (!task_ptrace(p) &&
|
2009-04-03 07:58:19 +08:00
|
|
|
p->exit_state == EXIT_ZOMBIE && thread_group_empty(p)) {
|
|
|
|
|
do_notify_parent(p, p->exit_signal);
|
|
|
|
|
if (task_detached(p)) {
|
|
|
|
|
p->exit_state = EXIT_DEAD;
|
|
|
|
|
list_move_tail(&p->sibling, dead);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
kill_orphaned_pgrp(p, father);
|
|
|
|
|
}
|
|
|
|
|
|
pid namespaces: rework forget_original_parent()
A pid namespace is a "view" of a particular set of tasks on the system. They
work in a similar way to filesystem namespaces. A file (or a process) can be
accessed in multiple namespaces, but it may have a different name in each. In
a filesystem, this name might be /etc/passwd in one namespace, but
/chroot/etc/passwd in another.
For processes, a process may have pid 1234 in one namespace, but be pid 1 in
another. This allows new pid namespaces to have basically arbitrary pids, and
not have to worry about what pids exist in other namespaces. This is
essential for checkpoint/restart where a restarted process's pid might collide
with an existing process on the system's pid.
In this particular implementation, pid namespaces have a parent-child
relationship, just like processes. A process in a pid namespace may see all
of the processes in the same namespace, as well as all of the processes in all
of the namespaces which are children of its namespace. Processes may not,
however, see others which are in their parent's namespace, but not in their
own. The same goes for sibling namespaces.
The know issue to be solved in the nearest future is signal handling in the
namespace boundary. That is, currently the namespace's init is treated like
an ordinary task that can be killed from within an namespace. Ideally, the
signal handling by the namespace's init should have two sides: when signaling
the init from its namespace, the init should look like a real init task, i.e.
receive only those signals, that is explicitly wants to; when signaling the
init from one of the parent namespaces, init should look like an ordinary
task, i.e. receive any signal, only taking the general permissions into
account.
The pid namespace was developed by Pavel Emlyanov and Sukadev Bhattiprolu and
we eventually came to almost the same implementation, which differed in some
details. This set is based on Pavel's patches, but it includes comments and
patches that from Sukadev.
Many thanks to Oleg, who reviewed the patches, pointed out many BUGs and made
valuable advises on how to make this set cleaner.
This patch:
We have to call exit_task_namespaces() only after the exiting task has
reparented all his children and is sure that no other threads will reparent
theirs for it. Why this is needed is explained in appropriate patch. This
one only reworks the forget_original_parent() so that after calling this a
task cannot be/become parent of any other task.
We check PF_EXITING instead of ->exit_state while choosing the new parent.
Note that tasklits_lock acts as a barrier, everyone who takes tasklist after
us (when forget_original_parent() drops it) must see PF_EXITING.
The other changes are just cleanups. They just move some code from
exit_notify to forget_original_parent(). It is a bit silly to declare
ptrace_dead in exit_notify(), take tasklist, pass ptrace_dead to
forget_original_parent(), unlock-lock-unlock tasklist, and then use
ptrace_dead.
Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru>
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Cc: Sukadev Bhattiprolu <sukadev@us.ibm.com>
Cc: Paul Menage <menage@google.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-19 14:40:00 +08:00
|
|
|
static void forget_original_parent(struct task_struct *father)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2008-09-03 05:35:49 +08:00
|
|
|
struct task_struct *p, *n, *reaper;
|
2009-04-03 07:58:19 +08:00
|
|
|
LIST_HEAD(dead_children);
|
pid namespaces: rework forget_original_parent()
A pid namespace is a "view" of a particular set of tasks on the system. They
work in a similar way to filesystem namespaces. A file (or a process) can be
accessed in multiple namespaces, but it may have a different name in each. In
a filesystem, this name might be /etc/passwd in one namespace, but
/chroot/etc/passwd in another.
For processes, a process may have pid 1234 in one namespace, but be pid 1 in
another. This allows new pid namespaces to have basically arbitrary pids, and
not have to worry about what pids exist in other namespaces. This is
essential for checkpoint/restart where a restarted process's pid might collide
with an existing process on the system's pid.
In this particular implementation, pid namespaces have a parent-child
relationship, just like processes. A process in a pid namespace may see all
of the processes in the same namespace, as well as all of the processes in all
of the namespaces which are children of its namespace. Processes may not,
however, see others which are in their parent's namespace, but not in their
own. The same goes for sibling namespaces.
The know issue to be solved in the nearest future is signal handling in the
namespace boundary. That is, currently the namespace's init is treated like
an ordinary task that can be killed from within an namespace. Ideally, the
signal handling by the namespace's init should have two sides: when signaling
the init from its namespace, the init should look like a real init task, i.e.
receive only those signals, that is explicitly wants to; when signaling the
init from one of the parent namespaces, init should look like an ordinary
task, i.e. receive any signal, only taking the general permissions into
account.
The pid namespace was developed by Pavel Emlyanov and Sukadev Bhattiprolu and
we eventually came to almost the same implementation, which differed in some
details. This set is based on Pavel's patches, but it includes comments and
patches that from Sukadev.
Many thanks to Oleg, who reviewed the patches, pointed out many BUGs and made
valuable advises on how to make this set cleaner.
This patch:
We have to call exit_task_namespaces() only after the exiting task has
reparented all his children and is sure that no other threads will reparent
theirs for it. Why this is needed is explained in appropriate patch. This
one only reworks the forget_original_parent() so that after calling this a
task cannot be/become parent of any other task.
We check PF_EXITING instead of ->exit_state while choosing the new parent.
Note that tasklits_lock acts as a barrier, everyone who takes tasklist after
us (when forget_original_parent() drops it) must see PF_EXITING.
The other changes are just cleanups. They just move some code from
exit_notify to forget_original_parent(). It is a bit silly to declare
ptrace_dead in exit_notify(), take tasklist, pass ptrace_dead to
forget_original_parent(), unlock-lock-unlock tasklist, and then use
ptrace_dead.
Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru>
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Cc: Sukadev Bhattiprolu <sukadev@us.ibm.com>
Cc: Paul Menage <menage@google.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-19 14:40:00 +08:00
|
|
|
|
|
|
|
|
write_lock_irq(&tasklist_lock);
|
2010-08-11 09:03:07 +08:00
|
|
|
/*
|
|
|
|
|
* Note that exit_ptrace() and find_new_reaper() might
|
|
|
|
|
* drop tasklist_lock and reacquire it.
|
|
|
|
|
*/
|
|
|
|
|
exit_ptrace(father);
|
2008-09-03 05:35:49 +08:00
|
|
|
reaper = find_new_reaper(father);
|
2008-03-25 09:36:23 +08:00
|
|
|
|
2007-10-19 14:39:57 +08:00
|
|
|
list_for_each_entry_safe(p, n, &father->children, sibling) {
|
2009-12-18 07:27:15 +08:00
|
|
|
struct task_struct *t = p;
|
|
|
|
|
do {
|
|
|
|
|
t->real_parent = reaper;
|
|
|
|
|
if (t->parent == father) {
|
|
|
|
|
BUG_ON(task_ptrace(t));
|
|
|
|
|
t->parent = t->real_parent;
|
|
|
|
|
}
|
|
|
|
|
if (t->pdeath_signal)
|
|
|
|
|
group_send_sig_info(t->pdeath_signal,
|
|
|
|
|
SEND_SIG_NOINFO, t);
|
|
|
|
|
} while_each_thread(p, t);
|
|
|
|
|
reparent_leader(father, p, &dead_children);
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
pid namespaces: rework forget_original_parent()
A pid namespace is a "view" of a particular set of tasks on the system. They
work in a similar way to filesystem namespaces. A file (or a process) can be
accessed in multiple namespaces, but it may have a different name in each. In
a filesystem, this name might be /etc/passwd in one namespace, but
/chroot/etc/passwd in another.
For processes, a process may have pid 1234 in one namespace, but be pid 1 in
another. This allows new pid namespaces to have basically arbitrary pids, and
not have to worry about what pids exist in other namespaces. This is
essential for checkpoint/restart where a restarted process's pid might collide
with an existing process on the system's pid.
In this particular implementation, pid namespaces have a parent-child
relationship, just like processes. A process in a pid namespace may see all
of the processes in the same namespace, as well as all of the processes in all
of the namespaces which are children of its namespace. Processes may not,
however, see others which are in their parent's namespace, but not in their
own. The same goes for sibling namespaces.
The know issue to be solved in the nearest future is signal handling in the
namespace boundary. That is, currently the namespace's init is treated like
an ordinary task that can be killed from within an namespace. Ideally, the
signal handling by the namespace's init should have two sides: when signaling
the init from its namespace, the init should look like a real init task, i.e.
receive only those signals, that is explicitly wants to; when signaling the
init from one of the parent namespaces, init should look like an ordinary
task, i.e. receive any signal, only taking the general permissions into
account.
The pid namespace was developed by Pavel Emlyanov and Sukadev Bhattiprolu and
we eventually came to almost the same implementation, which differed in some
details. This set is based on Pavel's patches, but it includes comments and
patches that from Sukadev.
Many thanks to Oleg, who reviewed the patches, pointed out many BUGs and made
valuable advises on how to make this set cleaner.
This patch:
We have to call exit_task_namespaces() only after the exiting task has
reparented all his children and is sure that no other threads will reparent
theirs for it. Why this is needed is explained in appropriate patch. This
one only reworks the forget_original_parent() so that after calling this a
task cannot be/become parent of any other task.
We check PF_EXITING instead of ->exit_state while choosing the new parent.
Note that tasklits_lock acts as a barrier, everyone who takes tasklist after
us (when forget_original_parent() drops it) must see PF_EXITING.
The other changes are just cleanups. They just move some code from
exit_notify to forget_original_parent(). It is a bit silly to declare
ptrace_dead in exit_notify(), take tasklist, pass ptrace_dead to
forget_original_parent(), unlock-lock-unlock tasklist, and then use
ptrace_dead.
Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru>
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Cc: Sukadev Bhattiprolu <sukadev@us.ibm.com>
Cc: Paul Menage <menage@google.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-19 14:40:00 +08:00
|
|
|
write_unlock_irq(&tasklist_lock);
|
2009-04-03 07:58:19 +08:00
|
|
|
|
pid namespaces: rework forget_original_parent()
A pid namespace is a "view" of a particular set of tasks on the system. They
work in a similar way to filesystem namespaces. A file (or a process) can be
accessed in multiple namespaces, but it may have a different name in each. In
a filesystem, this name might be /etc/passwd in one namespace, but
/chroot/etc/passwd in another.
For processes, a process may have pid 1234 in one namespace, but be pid 1 in
another. This allows new pid namespaces to have basically arbitrary pids, and
not have to worry about what pids exist in other namespaces. This is
essential for checkpoint/restart where a restarted process's pid might collide
with an existing process on the system's pid.
In this particular implementation, pid namespaces have a parent-child
relationship, just like processes. A process in a pid namespace may see all
of the processes in the same namespace, as well as all of the processes in all
of the namespaces which are children of its namespace. Processes may not,
however, see others which are in their parent's namespace, but not in their
own. The same goes for sibling namespaces.
The know issue to be solved in the nearest future is signal handling in the
namespace boundary. That is, currently the namespace's init is treated like
an ordinary task that can be killed from within an namespace. Ideally, the
signal handling by the namespace's init should have two sides: when signaling
the init from its namespace, the init should look like a real init task, i.e.
receive only those signals, that is explicitly wants to; when signaling the
init from one of the parent namespaces, init should look like an ordinary
task, i.e. receive any signal, only taking the general permissions into
account.
The pid namespace was developed by Pavel Emlyanov and Sukadev Bhattiprolu and
we eventually came to almost the same implementation, which differed in some
details. This set is based on Pavel's patches, but it includes comments and
patches that from Sukadev.
Many thanks to Oleg, who reviewed the patches, pointed out many BUGs and made
valuable advises on how to make this set cleaner.
This patch:
We have to call exit_task_namespaces() only after the exiting task has
reparented all his children and is sure that no other threads will reparent
theirs for it. Why this is needed is explained in appropriate patch. This
one only reworks the forget_original_parent() so that after calling this a
task cannot be/become parent of any other task.
We check PF_EXITING instead of ->exit_state while choosing the new parent.
Note that tasklits_lock acts as a barrier, everyone who takes tasklist after
us (when forget_original_parent() drops it) must see PF_EXITING.
The other changes are just cleanups. They just move some code from
exit_notify to forget_original_parent(). It is a bit silly to declare
ptrace_dead in exit_notify(), take tasklist, pass ptrace_dead to
forget_original_parent(), unlock-lock-unlock tasklist, and then use
ptrace_dead.
Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru>
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Cc: Sukadev Bhattiprolu <sukadev@us.ibm.com>
Cc: Paul Menage <menage@google.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-19 14:40:00 +08:00
|
|
|
BUG_ON(!list_empty(&father->children));
|
|
|
|
|
|
2009-04-03 07:58:19 +08:00
|
|
|
list_for_each_entry_safe(p, n, &dead_children, sibling) {
|
|
|
|
|
list_del_init(&p->sibling);
|
2009-04-03 07:58:18 +08:00
|
|
|
release_task(p);
|
|
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Send signals to all our closest relatives so that they know
|
|
|
|
|
* to properly mourn us..
|
|
|
|
|
*/
|
2008-03-03 02:44:44 +08:00
|
|
|
static void exit_notify(struct task_struct *tsk, int group_dead)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2008-07-26 10:45:54 +08:00
|
|
|
int signal;
|
|
|
|
|
void *cookie;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* This does two things:
|
|
|
|
|
*
|
|
|
|
|
* A. Make init inherit all the child processes
|
|
|
|
|
* B. Check to see if any process groups have become orphaned
|
|
|
|
|
* as a result of our exiting, and if they have any stopped
|
|
|
|
|
* jobs, send them a SIGHUP and then a SIGCONT. (POSIX 3.2.2.2)
|
|
|
|
|
*/
|
pid namespaces: rework forget_original_parent()
A pid namespace is a "view" of a particular set of tasks on the system. They
work in a similar way to filesystem namespaces. A file (or a process) can be
accessed in multiple namespaces, but it may have a different name in each. In
a filesystem, this name might be /etc/passwd in one namespace, but
/chroot/etc/passwd in another.
For processes, a process may have pid 1234 in one namespace, but be pid 1 in
another. This allows new pid namespaces to have basically arbitrary pids, and
not have to worry about what pids exist in other namespaces. This is
essential for checkpoint/restart where a restarted process's pid might collide
with an existing process on the system's pid.
In this particular implementation, pid namespaces have a parent-child
relationship, just like processes. A process in a pid namespace may see all
of the processes in the same namespace, as well as all of the processes in all
of the namespaces which are children of its namespace. Processes may not,
however, see others which are in their parent's namespace, but not in their
own. The same goes for sibling namespaces.
The know issue to be solved in the nearest future is signal handling in the
namespace boundary. That is, currently the namespace's init is treated like
an ordinary task that can be killed from within an namespace. Ideally, the
signal handling by the namespace's init should have two sides: when signaling
the init from its namespace, the init should look like a real init task, i.e.
receive only those signals, that is explicitly wants to; when signaling the
init from one of the parent namespaces, init should look like an ordinary
task, i.e. receive any signal, only taking the general permissions into
account.
The pid namespace was developed by Pavel Emlyanov and Sukadev Bhattiprolu and
we eventually came to almost the same implementation, which differed in some
details. This set is based on Pavel's patches, but it includes comments and
patches that from Sukadev.
Many thanks to Oleg, who reviewed the patches, pointed out many BUGs and made
valuable advises on how to make this set cleaner.
This patch:
We have to call exit_task_namespaces() only after the exiting task has
reparented all his children and is sure that no other threads will reparent
theirs for it. Why this is needed is explained in appropriate patch. This
one only reworks the forget_original_parent() so that after calling this a
task cannot be/become parent of any other task.
We check PF_EXITING instead of ->exit_state while choosing the new parent.
Note that tasklits_lock acts as a barrier, everyone who takes tasklist after
us (when forget_original_parent() drops it) must see PF_EXITING.
The other changes are just cleanups. They just move some code from
exit_notify to forget_original_parent(). It is a bit silly to declare
ptrace_dead in exit_notify(), take tasklist, pass ptrace_dead to
forget_original_parent(), unlock-lock-unlock tasklist, and then use
ptrace_dead.
Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru>
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Cc: Sukadev Bhattiprolu <sukadev@us.ibm.com>
Cc: Paul Menage <menage@google.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-19 14:40:00 +08:00
|
|
|
forget_original_parent(tsk);
|
2007-10-19 14:40:01 +08:00
|
|
|
exit_task_namespaces(tsk);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
pid namespaces: rework forget_original_parent()
A pid namespace is a "view" of a particular set of tasks on the system. They
work in a similar way to filesystem namespaces. A file (or a process) can be
accessed in multiple namespaces, but it may have a different name in each. In
a filesystem, this name might be /etc/passwd in one namespace, but
/chroot/etc/passwd in another.
For processes, a process may have pid 1234 in one namespace, but be pid 1 in
another. This allows new pid namespaces to have basically arbitrary pids, and
not have to worry about what pids exist in other namespaces. This is
essential for checkpoint/restart where a restarted process's pid might collide
with an existing process on the system's pid.
In this particular implementation, pid namespaces have a parent-child
relationship, just like processes. A process in a pid namespace may see all
of the processes in the same namespace, as well as all of the processes in all
of the namespaces which are children of its namespace. Processes may not,
however, see others which are in their parent's namespace, but not in their
own. The same goes for sibling namespaces.
The know issue to be solved in the nearest future is signal handling in the
namespace boundary. That is, currently the namespace's init is treated like
an ordinary task that can be killed from within an namespace. Ideally, the
signal handling by the namespace's init should have two sides: when signaling
the init from its namespace, the init should look like a real init task, i.e.
receive only those signals, that is explicitly wants to; when signaling the
init from one of the parent namespaces, init should look like an ordinary
task, i.e. receive any signal, only taking the general permissions into
account.
The pid namespace was developed by Pavel Emlyanov and Sukadev Bhattiprolu and
we eventually came to almost the same implementation, which differed in some
details. This set is based on Pavel's patches, but it includes comments and
patches that from Sukadev.
Many thanks to Oleg, who reviewed the patches, pointed out many BUGs and made
valuable advises on how to make this set cleaner.
This patch:
We have to call exit_task_namespaces() only after the exiting task has
reparented all his children and is sure that no other threads will reparent
theirs for it. Why this is needed is explained in appropriate patch. This
one only reworks the forget_original_parent() so that after calling this a
task cannot be/become parent of any other task.
We check PF_EXITING instead of ->exit_state while choosing the new parent.
Note that tasklits_lock acts as a barrier, everyone who takes tasklist after
us (when forget_original_parent() drops it) must see PF_EXITING.
The other changes are just cleanups. They just move some code from
exit_notify to forget_original_parent(). It is a bit silly to declare
ptrace_dead in exit_notify(), take tasklist, pass ptrace_dead to
forget_original_parent(), unlock-lock-unlock tasklist, and then use
ptrace_dead.
Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru>
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Cc: Sukadev Bhattiprolu <sukadev@us.ibm.com>
Cc: Paul Menage <menage@google.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-19 14:40:00 +08:00
|
|
|
write_lock_irq(&tasklist_lock);
|
2008-03-03 02:44:44 +08:00
|
|
|
if (group_dead)
|
|
|
|
|
kill_orphaned_pgrp(tsk->group_leader, NULL);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2007-08-04 05:04:41 +08:00
|
|
|
/* Let father know we died
|
2005-04-17 06:20:36 +08:00
|
|
|
*
|
|
|
|
|
* Thread signals are configurable, but you aren't going to use
|
2007-10-19 14:39:59 +08:00
|
|
|
* that to send signals to arbitary processes.
|
2005-04-17 06:20:36 +08:00
|
|
|
* That stops right now.
|
|
|
|
|
*
|
|
|
|
|
* If the parent exec id doesn't match the exec id we saved
|
|
|
|
|
* when we started then we know the parent has changed security
|
|
|
|
|
* domain.
|
|
|
|
|
*
|
|
|
|
|
* If our self_exec id doesn't match our parent_exec_id then
|
|
|
|
|
* we have changed execution domain as these two values started
|
|
|
|
|
* the same after a fork.
|
|
|
|
|
*/
|
2008-04-30 15:53:11 +08:00
|
|
|
if (tsk->exit_signal != SIGCHLD && !task_detached(tsk) &&
|
2008-03-03 02:44:40 +08:00
|
|
|
(tsk->parent_exec_id != tsk->real_parent->self_exec_id ||
|
2009-04-06 22:16:02 +08:00
|
|
|
tsk->self_exec_id != tsk->parent_exec_id))
|
2005-04-17 06:20:36 +08:00
|
|
|
tsk->exit_signal = SIGCHLD;
|
|
|
|
|
|
2008-07-26 10:45:54 +08:00
|
|
|
signal = tracehook_notify_death(tsk, &cookie, group_dead);
|
2008-07-31 17:04:09 +08:00
|
|
|
if (signal >= 0)
|
2008-07-26 10:45:54 +08:00
|
|
|
signal = do_notify_parent(tsk, signal);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2008-07-31 17:04:09 +08:00
|
|
|
tsk->exit_state = signal == DEATH_REAP ? EXIT_DEAD : EXIT_ZOMBIE;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2010-05-27 05:43:10 +08:00
|
|
|
/* mt-exec, de_thread() is waiting for group leader */
|
|
|
|
|
if (unlikely(tsk->signal->notify_count < 0))
|
2007-10-17 14:27:23 +08:00
|
|
|
wake_up_process(tsk->signal->group_exit_task);
|
2005-04-17 06:20:36 +08:00
|
|
|
write_unlock_irq(&tasklist_lock);
|
|
|
|
|
|
2008-07-26 10:45:54 +08:00
|
|
|
tracehook_report_death(tsk, signal, cookie, group_dead);
|
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/* If the process is dead, release it - nobody will wait for it */
|
2008-07-31 17:04:09 +08:00
|
|
|
if (signal == DEATH_REAP)
|
2005-04-17 06:20:36 +08:00
|
|
|
release_task(tsk);
|
|
|
|
|
}
|
|
|
|
|
|
2007-07-16 14:38:48 +08:00
|
|
|
#ifdef CONFIG_DEBUG_STACK_USAGE
|
|
|
|
|
static void check_stack_usage(void)
|
|
|
|
|
{
|
|
|
|
|
static DEFINE_SPINLOCK(low_water_lock);
|
|
|
|
|
static int lowest_to_date = THREAD_SIZE;
|
|
|
|
|
unsigned long free;
|
|
|
|
|
|
2008-04-23 05:38:23 +08:00
|
|
|
free = stack_not_used(current);
|
2007-07-16 14:38:48 +08:00
|
|
|
|
|
|
|
|
if (free >= lowest_to_date)
|
|
|
|
|
return;
|
|
|
|
|
|
|
|
|
|
spin_lock(&low_water_lock);
|
|
|
|
|
if (free < lowest_to_date) {
|
|
|
|
|
printk(KERN_WARNING "%s used greatest stack depth: %lu bytes "
|
|
|
|
|
"left\n",
|
|
|
|
|
current->comm, free);
|
|
|
|
|
lowest_to_date = free;
|
|
|
|
|
}
|
|
|
|
|
spin_unlock(&low_water_lock);
|
|
|
|
|
}
|
|
|
|
|
#else
|
|
|
|
|
static inline void check_stack_usage(void) {}
|
|
|
|
|
#endif
|
|
|
|
|
|
2008-02-08 20:19:53 +08:00
|
|
|
NORET_TYPE void do_exit(long code)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
|
struct task_struct *tsk = current;
|
|
|
|
|
int group_dead;
|
|
|
|
|
|
|
|
|
|
profile_task_exit(tsk);
|
|
|
|
|
|
2005-06-27 16:55:12 +08:00
|
|
|
WARN_ON(atomic_read(&tsk->fs_excl));
|
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
if (unlikely(in_interrupt()))
|
|
|
|
|
panic("Aiee, killing interrupt handler!");
|
|
|
|
|
if (unlikely(!tsk->pid))
|
|
|
|
|
panic("Attempted to kill the idle task!");
|
|
|
|
|
|
2010-12-03 06:31:21 +08:00
|
|
|
/*
|
|
|
|
|
* If do_exit is called because this processes oopsed, it's possible
|
|
|
|
|
* that get_fs() was left as KERNEL_DS, so reset it to USER_DS before
|
|
|
|
|
* continuing. Amongst other possible reasons, this is to prevent
|
|
|
|
|
* mm_release()->clear_child_tid() from writing to a user-controlled
|
|
|
|
|
* kernel address.
|
|
|
|
|
*/
|
|
|
|
|
set_fs(USER_DS);
|
|
|
|
|
|
2008-07-26 10:45:46 +08:00
|
|
|
tracehook_report_exit(&code);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2009-09-02 16:13:40 +08:00
|
|
|
validate_creds_for_do_exit(tsk);
|
|
|
|
|
|
2005-06-23 15:09:13 +08:00
|
|
|
/*
|
|
|
|
|
* We're taking recursive faults here in do_exit. Safest is to just
|
|
|
|
|
* leave this task alone and wait for reboot.
|
|
|
|
|
*/
|
|
|
|
|
if (unlikely(tsk->flags & PF_EXITING)) {
|
|
|
|
|
printk(KERN_ALERT
|
|
|
|
|
"Fixing recursive fault but reboot is needed!\n");
|
2007-06-09 04:47:00 +08:00
|
|
|
/*
|
|
|
|
|
* We can do this unlocked here. The futex code uses
|
|
|
|
|
* this flag just to verify whether the pi state
|
|
|
|
|
* cleanup has been done or not. In the worst case it
|
|
|
|
|
* loops once more. We pretend that the cleanup was
|
|
|
|
|
* done as there is no way to return. Either the
|
|
|
|
|
* OWNER_DIED bit is set by now or we push the blocked
|
|
|
|
|
* task into the wait for ever nirwana as well.
|
|
|
|
|
*/
|
|
|
|
|
tsk->flags |= PF_EXITPIDONE;
|
2005-06-23 15:09:13 +08:00
|
|
|
set_current_state(TASK_UNINTERRUPTIBLE);
|
|
|
|
|
schedule();
|
|
|
|
|
}
|
|
|
|
|
|
2009-03-24 01:28:15 +08:00
|
|
|
exit_irq_thread();
|
|
|
|
|
|
2008-02-08 20:19:12 +08:00
|
|
|
exit_signals(tsk); /* sets PF_EXITING */
|
2007-06-09 04:47:00 +08:00
|
|
|
/*
|
|
|
|
|
* tsk->flags are checked in the futex code to protect against
|
|
|
|
|
* an exiting task cleaning up the robust pi futexes.
|
|
|
|
|
*/
|
2007-10-17 14:26:47 +08:00
|
|
|
smp_mb();
|
2009-11-17 21:54:03 +08:00
|
|
|
raw_spin_unlock_wait(&tsk->pi_lock);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
if (unlikely(in_atomic()))
|
|
|
|
|
printk(KERN_INFO "note: %s[%d] exited with preempt_count %d\n",
|
2007-10-19 14:40:40 +08:00
|
|
|
current->comm, task_pid_nr(current),
|
2005-04-17 06:20:36 +08:00
|
|
|
preempt_count());
|
|
|
|
|
|
|
|
|
|
acct_update_integrals(tsk);
|
2010-03-06 05:41:40 +08:00
|
|
|
/* sync mm's RSS info before statistics gathering */
|
2010-04-07 05:34:42 +08:00
|
|
|
if (tsk->mm)
|
|
|
|
|
sync_mm_rss(tsk, tsk->mm);
|
2005-04-17 06:20:36 +08:00
|
|
|
group_dead = atomic_dec_and_test(&tsk->signal->live);
|
2005-08-05 07:49:32 +08:00
|
|
|
if (group_dead) {
|
2007-06-09 04:47:00 +08:00
|
|
|
hrtimer_cancel(&tsk->signal->real_timer);
|
2005-10-22 06:03:29 +08:00
|
|
|
exit_itimers(tsk->signal);
|
getrusage: fill ru_maxrss value
Make ->ru_maxrss value in struct rusage filled accordingly to rss hiwater
mark. This struct is filled as a parameter to getrusage syscall.
->ru_maxrss value is set to KBs which is the way it is done in BSD
systems. /usr/bin/time (gnu time) application converts ->ru_maxrss to KBs
which seems to be incorrect behavior. Maintainer of this util was
notified by me with the patch which corrects it and cc'ed.
To make this happen we extend struct signal_struct by two fields. The
first one is ->maxrss which we use to store rss hiwater of the task. The
second one is ->cmaxrss which we use to store highest rss hiwater of all
task childs. These values are used in k_getrusage() to actually fill
->ru_maxrss. k_getrusage() uses current rss hiwater value directly if mm
struct exists.
Note:
exec() clear mm->hiwater_rss, but doesn't clear sig->maxrss.
it is intetionally behavior. *BSD getrusage have exec() inheriting.
test programs
========================================================
getrusage.c
===========
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/types.h>
#include <sys/time.h>
#include <sys/resource.h>
#include <sys/types.h>
#include <sys/wait.h>
#include <unistd.h>
#include <signal.h>
#include <sys/mman.h>
#include "common.h"
#define err(str) perror(str), exit(1)
int main(int argc, char** argv)
{
int status;
printf("allocate 100MB\n");
consume(100);
printf("testcase1: fork inherit? \n");
printf(" expect: initial.self ~= child.self\n");
show_rusage("initial");
if (__fork()) {
wait(&status);
} else {
show_rusage("fork child");
_exit(0);
}
printf("\n");
printf("testcase2: fork inherit? (cont.) \n");
printf(" expect: initial.children ~= 100MB, but child.children = 0\n");
show_rusage("initial");
if (__fork()) {
wait(&status);
} else {
show_rusage("child");
_exit(0);
}
printf("\n");
printf("testcase3: fork + malloc \n");
printf(" expect: child.self ~= initial.self + 50MB\n");
show_rusage("initial");
if (__fork()) {
wait(&status);
} else {
printf("allocate +50MB\n");
consume(50);
show_rusage("fork child");
_exit(0);
}
printf("\n");
printf("testcase4: grandchild maxrss\n");
printf(" expect: post_wait.children ~= 300MB\n");
show_rusage("initial");
if (__fork()) {
wait(&status);
show_rusage("post_wait");
} else {
system("./child -n 0 -g 300");
_exit(0);
}
printf("\n");
printf("testcase5: zombie\n");
printf(" expect: pre_wait ~= initial, IOW the zombie process is not accounted.\n");
printf(" post_wait ~= 400MB, IOW wait() collect child's max_rss. \n");
show_rusage("initial");
if (__fork()) {
sleep(1); /* children become zombie */
show_rusage("pre_wait");
wait(&status);
show_rusage("post_wait");
} else {
system("./child -n 400");
_exit(0);
}
printf("\n");
printf("testcase6: SIG_IGN\n");
printf(" expect: initial ~= after_zombie (child's 500MB alloc should be ignored).\n");
show_rusage("initial");
signal(SIGCHLD, SIG_IGN);
if (__fork()) {
sleep(1); /* children become zombie */
show_rusage("after_zombie");
} else {
system("./child -n 500");
_exit(0);
}
printf("\n");
signal(SIGCHLD, SIG_DFL);
printf("testcase7: exec (without fork) \n");
printf(" expect: initial ~= exec \n");
show_rusage("initial");
execl("./child", "child", "-v", NULL);
return 0;
}
child.c
=======
#include <sys/types.h>
#include <unistd.h>
#include <sys/types.h>
#include <sys/wait.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/types.h>
#include <sys/time.h>
#include <sys/resource.h>
#include "common.h"
int main(int argc, char** argv)
{
int status;
int c;
long consume_size = 0;
long grandchild_consume_size = 0;
int show = 0;
while ((c = getopt(argc, argv, "n:g:v")) != -1) {
switch (c) {
case 'n':
consume_size = atol(optarg);
break;
case 'v':
show = 1;
break;
case 'g':
grandchild_consume_size = atol(optarg);
break;
default:
break;
}
}
if (show)
show_rusage("exec");
if (consume_size) {
printf("child alloc %ldMB\n", consume_size);
consume(consume_size);
}
if (grandchild_consume_size) {
if (fork()) {
wait(&status);
} else {
printf("grandchild alloc %ldMB\n", grandchild_consume_size);
consume(grandchild_consume_size);
exit(0);
}
}
return 0;
}
common.c
========
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/types.h>
#include <sys/time.h>
#include <sys/resource.h>
#include <sys/types.h>
#include <sys/wait.h>
#include <unistd.h>
#include <signal.h>
#include <sys/mman.h>
#include "common.h"
#define err(str) perror(str), exit(1)
void show_rusage(char *prefix)
{
int err, err2;
struct rusage rusage_self;
struct rusage rusage_children;
printf("%s: ", prefix);
err = getrusage(RUSAGE_SELF, &rusage_self);
if (!err)
printf("self %ld ", rusage_self.ru_maxrss);
err2 = getrusage(RUSAGE_CHILDREN, &rusage_children);
if (!err2)
printf("children %ld ", rusage_children.ru_maxrss);
printf("\n");
}
/* Some buggy OS need this worthless CPU waste. */
void make_pagefault(void)
{
void *addr;
int size = getpagesize();
int i;
for (i=0; i<1000; i++) {
addr = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANON, -1, 0);
if (addr == MAP_FAILED)
err("make_pagefault");
memset(addr, 0, size);
munmap(addr, size);
}
}
void consume(int mega)
{
size_t sz = mega * 1024 * 1024;
void *ptr;
ptr = malloc(sz);
memset(ptr, 0, sz);
make_pagefault();
}
pid_t __fork(void)
{
pid_t pid;
pid = fork();
make_pagefault();
return pid;
}
common.h
========
void show_rusage(char *prefix);
void make_pagefault(void);
void consume(int mega);
pid_t __fork(void);
FreeBSD result (expected result)
========================================================
allocate 100MB
testcase1: fork inherit?
expect: initial.self ~= child.self
initial: self 103492 children 0
fork child: self 103540 children 0
testcase2: fork inherit? (cont.)
expect: initial.children ~= 100MB, but child.children = 0
initial: self 103540 children 103540
child: self 103564 children 0
testcase3: fork + malloc
expect: child.self ~= initial.self + 50MB
initial: self 103564 children 103564
allocate +50MB
fork child: self 154860 children 0
testcase4: grandchild maxrss
expect: post_wait.children ~= 300MB
initial: self 103564 children 154860
grandchild alloc 300MB
post_wait: self 103564 children 308720
testcase5: zombie
expect: pre_wait ~= initial, IOW the zombie process is not accounted.
post_wait ~= 400MB, IOW wait() collect child's max_rss.
initial: self 103564 children 308720
child alloc 400MB
pre_wait: self 103564 children 308720
post_wait: self 103564 children 411312
testcase6: SIG_IGN
expect: initial ~= after_zombie (child's 500MB alloc should be ignored).
initial: self 103564 children 411312
child alloc 500MB
after_zombie: self 103624 children 411312
testcase7: exec (without fork)
expect: initial ~= exec
initial: self 103624 children 411312
exec: self 103624 children 411312
Linux result (actual test result)
========================================================
allocate 100MB
testcase1: fork inherit?
expect: initial.self ~= child.self
initial: self 102848 children 0
fork child: self 102572 children 0
testcase2: fork inherit? (cont.)
expect: initial.children ~= 100MB, but child.children = 0
initial: self 102876 children 102644
child: self 102572 children 0
testcase3: fork + malloc
expect: child.self ~= initial.self + 50MB
initial: self 102876 children 102644
allocate +50MB
fork child: self 153804 children 0
testcase4: grandchild maxrss
expect: post_wait.children ~= 300MB
initial: self 102876 children 153864
grandchild alloc 300MB
post_wait: self 102876 children 307536
testcase5: zombie
expect: pre_wait ~= initial, IOW the zombie process is not accounted.
post_wait ~= 400MB, IOW wait() collect child's max_rss.
initial: self 102876 children 307536
child alloc 400MB
pre_wait: self 102876 children 307536
post_wait: self 102876 children 410076
testcase6: SIG_IGN
expect: initial ~= after_zombie (child's 500MB alloc should be ignored).
initial: self 102876 children 410076
child alloc 500MB
after_zombie: self 102880 children 410076
testcase7: exec (without fork)
expect: initial ~= exec
initial: self 102880 children 410076
exec: self 102880 children 410076
Signed-off-by: Jiri Pirko <jpirko@redhat.com>
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Hugh Dickins <hugh.dickins@tiscali.co.uk>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-09-23 07:44:10 +08:00
|
|
|
if (tsk->mm)
|
|
|
|
|
setmax_mm_hiwater_rss(&tsk->signal->maxrss, tsk->mm);
|
2005-08-05 07:49:32 +08:00
|
|
|
}
|
2006-06-25 20:49:25 +08:00
|
|
|
acct_collect(code, group_dead);
|
Audit: add TTY input auditing
Add TTY input auditing, used to audit system administrator's actions. This is
required by various security standards such as DCID 6/3 and PCI to provide
non-repudiation of administrator's actions and to allow a review of past
actions if the administrator seems to overstep their duties or if the system
becomes misconfigured for unknown reasons. These requirements do not make it
necessary to audit TTY output as well.
Compared to an user-space keylogger, this approach records TTY input using the
audit subsystem, correlated with other audit events, and it is completely
transparent to the user-space application (e.g. the console ioctls still
work).
TTY input auditing works on a higher level than auditing all system calls
within the session, which would produce an overwhelming amount of mostly
useless audit events.
Add an "audit_tty" attribute, inherited across fork (). Data read from TTYs
by process with the attribute is sent to the audit subsystem by the kernel.
The audit netlink interface is extended to allow modifying the audit_tty
attribute, and to allow sending explanatory audit events from user-space (for
example, a shell might send an event containing the final command, after the
interactive command-line editing and history expansion is performed, which
might be difficult to decipher from the TTY input alone).
Because the "audit_tty" attribute is inherited across fork (), it would be set
e.g. for sshd restarted within an audited session. To prevent this, the
audit_tty attribute is cleared when a process with no open TTY file
descriptors (e.g. after daemon startup) opens a TTY.
See https://www.redhat.com/archives/linux-audit/2007-June/msg00000.html for a
more detailed rationale document for an older version of this patch.
[akpm@linux-foundation.org: build fix]
Signed-off-by: Miloslav Trmac <mitr@redhat.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Alan Cox <alan@lxorguk.ukuu.org.uk>
Cc: Paul Fulghum <paulkf@microgate.com>
Cc: Casey Schaufler <casey@schaufler-ca.com>
Cc: Steve Grubb <sgrubb@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-16 14:40:56 +08:00
|
|
|
if (group_dead)
|
|
|
|
|
tty_audit_exit();
|
2006-03-30 09:30:19 +08:00
|
|
|
if (unlikely(tsk->audit_context))
|
|
|
|
|
audit_free(tsk);
|
2006-12-07 12:36:51 +08:00
|
|
|
|
2007-08-31 14:56:23 +08:00
|
|
|
tsk->exit_code = code;
|
2006-12-07 12:36:51 +08:00
|
|
|
taskstats_exit(tsk, group_dead);
|
2006-07-14 15:24:40 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
exit_mm(tsk);
|
|
|
|
|
|
2006-06-25 20:49:24 +08:00
|
|
|
if (group_dead)
|
2006-06-25 20:49:25 +08:00
|
|
|
acct_process();
|
tracing, sched: LTTng instrumentation - scheduler
Instrument the scheduler activity (sched_switch, migration, wakeups,
wait for a task, signal delivery) and process/thread
creation/destruction (fork, exit, kthread stop). Actually, kthread
creation is not instrumented in this patch because it is architecture
dependent. It allows to connect tracers such as ftrace which detects
scheduling latencies, good/bad scheduler decisions. Tools like LTTng can
export this scheduler information along with instrumentation of the rest
of the kernel activity to perform post-mortem analysis on the scheduler
activity.
About the performance impact of tracepoints (which is comparable to
markers), even without immediate values optimizations, tests done by
Hideo Aoki on ia64 show no regression. His test case was using hackbench
on a kernel where scheduler instrumentation (about 5 events in code
scheduler code) was added. See the "Tracepoints" patch header for
performance result detail.
Changelog :
- Change instrumentation location and parameter to match ftrace
instrumentation, previously done with kernel markers.
[ mingo@elte.hu: conflict resolutions ]
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
Acked-by: 'Peter Zijlstra' <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-07-19 00:16:17 +08:00
|
|
|
trace_sched_process_exit(tsk);
|
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
exit_sem(tsk);
|
2008-04-22 17:35:42 +08:00
|
|
|
exit_files(tsk);
|
|
|
|
|
exit_fs(tsk);
|
2007-07-16 14:38:48 +08:00
|
|
|
check_stack_usage();
|
2005-04-17 06:20:36 +08:00
|
|
|
exit_thread();
|
2011-01-04 00:20:01 +08:00
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Flush inherited counters to the parent - before the parent
|
|
|
|
|
* gets woken up by child-exit notifications.
|
|
|
|
|
*
|
|
|
|
|
* because of cgroup mode, must be called before cgroup_exit()
|
|
|
|
|
*/
|
|
|
|
|
perf_event_exit_task(tsk);
|
|
|
|
|
|
2007-10-19 14:39:33 +08:00
|
|
|
cgroup_exit(tsk, 1);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2009-11-30 21:18:45 +08:00
|
|
|
if (group_dead)
|
2005-04-17 06:20:36 +08:00
|
|
|
disassociate_ctty(1);
|
|
|
|
|
|
2005-11-14 08:06:55 +08:00
|
|
|
module_put(task_thread_info(tsk)->exec_domain->module);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2005-11-07 16:59:16 +08:00
|
|
|
proc_exit_connector(tsk);
|
2009-05-17 17:08:41 +08:00
|
|
|
|
2009-09-10 01:22:48 +08:00
|
|
|
/*
|
|
|
|
|
* FIXME: do that only when needed, using sched_exit tracepoint
|
|
|
|
|
*/
|
|
|
|
|
flush_ptrace_hw_breakpoint(tsk);
|
2009-05-17 17:08:41 +08:00
|
|
|
|
2008-03-03 02:44:44 +08:00
|
|
|
exit_notify(tsk, group_dead);
|
2005-04-17 06:20:36 +08:00
|
|
|
#ifdef CONFIG_NUMA
|
2010-05-25 05:32:08 +08:00
|
|
|
task_lock(tsk);
|
2008-04-28 17:13:08 +08:00
|
|
|
mpol_put(tsk->mempolicy);
|
2005-04-17 06:20:36 +08:00
|
|
|
tsk->mempolicy = NULL;
|
2010-05-25 05:32:08 +08:00
|
|
|
task_unlock(tsk);
|
2005-04-17 06:20:36 +08:00
|
|
|
#endif
|
2007-10-17 14:27:30 +08:00
|
|
|
#ifdef CONFIG_FUTEX
|
2006-06-27 17:54:58 +08:00
|
|
|
if (unlikely(current->pi_state_cache))
|
|
|
|
|
kfree(current->pi_state_cache);
|
2007-10-17 14:27:30 +08:00
|
|
|
#endif
|
2006-01-10 07:59:21 +08:00
|
|
|
/*
|
2006-07-03 15:24:33 +08:00
|
|
|
* Make sure we are holding no locks:
|
2006-01-10 07:59:21 +08:00
|
|
|
*/
|
2006-07-03 15:24:33 +08:00
|
|
|
debug_check_no_locks_held(tsk);
|
2007-06-09 04:47:00 +08:00
|
|
|
/*
|
|
|
|
|
* We can do this unlocked here. The futex code uses this flag
|
|
|
|
|
* just to verify whether the pi state cleanup has been done
|
|
|
|
|
* or not. In the worst case it loops once more.
|
|
|
|
|
*/
|
|
|
|
|
tsk->flags |= PF_EXITPIDONE;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2006-03-01 01:51:55 +08:00
|
|
|
if (tsk->io_context)
|
2009-12-04 21:52:42 +08:00
|
|
|
exit_io_context(tsk);
|
2006-03-01 01:51:55 +08:00
|
|
|
|
2006-04-11 19:52:07 +08:00
|
|
|
if (tsk->splice_pipe)
|
|
|
|
|
__free_pipe_info(tsk->splice_pipe);
|
|
|
|
|
|
2009-09-02 16:13:40 +08:00
|
|
|
validate_creds_for_do_exit(tsk);
|
|
|
|
|
|
2005-10-31 07:02:47 +08:00
|
|
|
preempt_disable();
|
rcu: Merge preemptable-RCU functionality into hierarchical RCU
Create a kernel/rcutree_plugin.h file that contains definitions
for preemptable RCU (or, under the #else branch of the #ifdef,
empty definitions for the classic non-preemptable semantics).
These definitions fit into plugins defined in kernel/rcutree.c
for this purpose.
This variant of preemptable RCU uses a new algorithm whose
read-side expense is roughly that of classic hierarchical RCU
under CONFIG_PREEMPT. This new algorithm's update-side expense
is similar to that of classic hierarchical RCU, and, in absence
of read-side preemption or blocking, is exactly that of classic
hierarchical RCU. Perhaps more important, this new algorithm
has a much simpler implementation, saving well over 1,000 lines
of code compared to mainline's implementation of preemptable
RCU, which will hopefully be retired in favor of this new
algorithm.
The simplifications are obtained by maintaining per-task
nesting state for running tasks, and using a simple
lock-protected algorithm to handle accounting when tasks block
within RCU read-side critical sections, making use of lessons
learned while creating numerous user-level RCU implementations
over the past 18 months.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: laijs@cn.fujitsu.com
Cc: dipankar@in.ibm.com
Cc: akpm@linux-foundation.org
Cc: mathieu.desnoyers@polymtl.ca
Cc: josht@linux.vnet.ibm.com
Cc: dvhltc@us.ibm.com
Cc: niv@us.ibm.com
Cc: peterz@infradead.org
Cc: rostedt@goodmis.org
LKML-Reference: <12509746134003-git-send-email->
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-08-23 04:56:52 +08:00
|
|
|
exit_rcu();
|
2006-09-29 17:01:10 +08:00
|
|
|
/* causes final put_task_struct in finish_task_switch(). */
|
2006-09-29 17:01:11 +08:00
|
|
|
tsk->state = TASK_DEAD;
|
2005-04-17 06:20:36 +08:00
|
|
|
schedule();
|
|
|
|
|
BUG();
|
|
|
|
|
/* Avoid "noreturn function does return". */
|
2006-09-29 17:00:42 +08:00
|
|
|
for (;;)
|
|
|
|
|
cpu_relax(); /* For when BUG is null */
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
2005-04-23 15:08:00 +08:00
|
|
|
EXPORT_SYMBOL_GPL(do_exit);
|
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
NORET_TYPE void complete_and_exit(struct completion *comp, long code)
|
|
|
|
|
{
|
|
|
|
|
if (comp)
|
|
|
|
|
complete(comp);
|
2006-09-29 17:01:10 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
do_exit(code);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
EXPORT_SYMBOL(complete_and_exit);
|
|
|
|
|
|
2009-01-14 21:14:09 +08:00
|
|
|
SYSCALL_DEFINE1(exit, int, error_code)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
|
do_exit((error_code&0xff)<<8);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Take down every thread in the group. This is called by fatal signals
|
|
|
|
|
* as well as by sys_exit_group (below).
|
|
|
|
|
*/
|
|
|
|
|
NORET_TYPE void
|
|
|
|
|
do_group_exit(int exit_code)
|
|
|
|
|
{
|
2008-04-30 15:52:36 +08:00
|
|
|
struct signal_struct *sig = current->signal;
|
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
BUG_ON(exit_code & 0x80); /* core dumps don't get here */
|
|
|
|
|
|
2008-04-30 15:52:36 +08:00
|
|
|
if (signal_group_exit(sig))
|
|
|
|
|
exit_code = sig->group_exit_code;
|
2005-04-17 06:20:36 +08:00
|
|
|
else if (!thread_group_empty(current)) {
|
|
|
|
|
struct sighand_struct *const sighand = current->sighand;
|
|
|
|
|
spin_lock_irq(&sighand->siglock);
|
2008-02-05 14:27:24 +08:00
|
|
|
if (signal_group_exit(sig))
|
2005-04-17 06:20:36 +08:00
|
|
|
/* Another thread got here before we took the lock. */
|
|
|
|
|
exit_code = sig->group_exit_code;
|
|
|
|
|
else {
|
|
|
|
|
sig->group_exit_code = exit_code;
|
2008-02-05 14:27:24 +08:00
|
|
|
sig->flags = SIGNAL_GROUP_EXIT;
|
2005-04-17 06:20:36 +08:00
|
|
|
zap_other_threads(current);
|
|
|
|
|
}
|
|
|
|
|
spin_unlock_irq(&sighand->siglock);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
do_exit(exit_code);
|
|
|
|
|
/* NOTREACHED */
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* this kills every thread in the thread group. Note that any externally
|
|
|
|
|
* wait4()-ing process will get the correct exit code - even if this
|
|
|
|
|
* thread is not the thread group leader.
|
|
|
|
|
*/
|
2009-01-14 21:14:09 +08:00
|
|
|
SYSCALL_DEFINE1(exit_group, int, error_code)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
|
do_group_exit((error_code & 0xff) << 8);
|
2009-01-14 21:13:54 +08:00
|
|
|
/* NOTREACHED */
|
|
|
|
|
return 0;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
2009-06-18 07:27:39 +08:00
|
|
|
struct wait_opts {
|
|
|
|
|
enum pid_type wo_type;
|
|
|
|
|
int wo_flags;
|
2009-06-18 07:27:42 +08:00
|
|
|
struct pid *wo_pid;
|
2009-06-18 07:27:39 +08:00
|
|
|
|
|
|
|
|
struct siginfo __user *wo_info;
|
|
|
|
|
int __user *wo_stat;
|
|
|
|
|
struct rusage __user *wo_rusage;
|
|
|
|
|
|
2009-09-24 06:56:46 +08:00
|
|
|
wait_queue_t child_wait;
|
2009-06-18 07:27:39 +08:00
|
|
|
int notask_error;
|
|
|
|
|
};
|
|
|
|
|
|
2009-09-24 06:56:49 +08:00
|
|
|
static inline
|
|
|
|
|
struct pid *task_pid_type(struct task_struct *task, enum pid_type type)
|
2008-02-08 20:19:14 +08:00
|
|
|
{
|
2009-09-24 06:56:49 +08:00
|
|
|
if (type != PIDTYPE_PID)
|
|
|
|
|
task = task->group_leader;
|
|
|
|
|
return task->pids[type].pid;
|
2008-02-08 20:19:14 +08:00
|
|
|
}
|
|
|
|
|
|
2009-09-24 06:56:49 +08:00
|
|
|
static int eligible_pid(struct wait_opts *wo, struct task_struct *p)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2009-09-24 06:56:48 +08:00
|
|
|
return wo->wo_type == PIDTYPE_MAX ||
|
|
|
|
|
task_pid_type(p, wo->wo_type) == wo->wo_pid;
|
|
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2009-09-24 06:56:48 +08:00
|
|
|
static int eligible_child(struct wait_opts *wo, struct task_struct *p)
|
|
|
|
|
{
|
|
|
|
|
if (!eligible_pid(wo, p))
|
|
|
|
|
return 0;
|
2005-04-17 06:20:36 +08:00
|
|
|
/* Wait for all children (clone and not) if __WALL is set;
|
|
|
|
|
* otherwise, wait for clone children *only* if __WCLONE is
|
|
|
|
|
* set; otherwise, wait for non-clone children *only*. (Note:
|
|
|
|
|
* A "clone" child here is one that reports to its parent
|
|
|
|
|
* using a signal other than SIGCHLD.) */
|
2009-06-18 07:27:39 +08:00
|
|
|
if (((p->exit_signal != SIGCHLD) ^ !!(wo->wo_flags & __WCLONE))
|
|
|
|
|
&& !(wo->wo_flags & __WALL))
|
2005-04-17 06:20:36 +08:00
|
|
|
return 0;
|
|
|
|
|
|
2008-03-31 09:41:25 +08:00
|
|
|
return 1;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
2009-06-18 07:27:39 +08:00
|
|
|
static int wait_noreap_copyout(struct wait_opts *wo, struct task_struct *p,
|
|
|
|
|
pid_t pid, uid_t uid, int why, int status)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2009-06-18 07:27:39 +08:00
|
|
|
struct siginfo __user *infop;
|
|
|
|
|
int retval = wo->wo_rusage
|
|
|
|
|
? getrusage(p, RUSAGE_BOTH, wo->wo_rusage) : 0;
|
2006-07-03 15:25:41 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
put_task_struct(p);
|
2009-06-18 07:27:39 +08:00
|
|
|
infop = wo->wo_info;
|
2009-09-24 06:56:52 +08:00
|
|
|
if (infop) {
|
|
|
|
|
if (!retval)
|
|
|
|
|
retval = put_user(SIGCHLD, &infop->si_signo);
|
|
|
|
|
if (!retval)
|
|
|
|
|
retval = put_user(0, &infop->si_errno);
|
|
|
|
|
if (!retval)
|
|
|
|
|
retval = put_user((short)why, &infop->si_code);
|
|
|
|
|
if (!retval)
|
|
|
|
|
retval = put_user(pid, &infop->si_pid);
|
|
|
|
|
if (!retval)
|
|
|
|
|
retval = put_user(uid, &infop->si_uid);
|
|
|
|
|
if (!retval)
|
|
|
|
|
retval = put_user(status, &infop->si_status);
|
|
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
if (!retval)
|
|
|
|
|
retval = pid;
|
|
|
|
|
return retval;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Handle sys_wait4 work for one task in state EXIT_ZOMBIE. We hold
|
|
|
|
|
* read_lock(&tasklist_lock) on entry. If we return zero, we still hold
|
|
|
|
|
* the lock and this task is uninteresting. If we return nonzero, we have
|
|
|
|
|
* released the lock and the system call should return.
|
|
|
|
|
*/
|
2009-06-18 07:27:39 +08:00
|
|
|
static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
|
unsigned long state;
|
wait_task_zombie: fix 2/3 races vs forget_original_parent()
Two threads, T1 and T2. T2 ptraces P, and P is not a child of ptracer's
thread group. P exits and goes to TASK_ZOMBIE.
T1 does wait_task_zombie(P):
P->exit_state = TASK_DEAD;
...
read_unlock(&tasklist_lock);
T2 does exit(), takes tasklist,
forget_original_parent() does
__ptrace_unlink(P) but doesn't
call do_notify_parent(P) because
p->exit_state == EXIT_DEAD.
Now, P is not visible to our process: __ptrace_unlink() removed it from
->children. We should send notification to P->parent and release P if and
only if SIGCHLD is ignored.
And we have 3 bugs:
1. P->parent does do_wait() and gets -ECHILD (P is on ->parent->children,
but its state is TASK_DEAD).
2. // wait_task_zombie() continues
if (put_user(...)) {
// TODO: is this safe?
p->exit_state = EXIT_ZOMBIE;
return;
}
we return without notification/release, task_struct leaked.
Solution: ignore -EFAULT and proceed. It is an application's bug if
we can't fill infop/stat_addr (in case of VM_FAULT_OOM we have much
more problems).
3. // wait_task_zombie() continues
if (p->real_parent != p->parent) {
// Not taken, it was untraced'ed
...
}
release_task(p);
we released the task which we shouldn't.
Solution: check ->real_parent != ->parent before, under tasklist_lock,
but use ptrace_unlink() instead of __ptrace_unlink() to check ->ptrace.
This patch hopefully solves 2 and 3, the 1st bug will be fixed later, we need
some cleanups in forget_original_parent/reparent_thread.
However, the first race is very unlikely and not critical, so I hope it makes
sense to fix 1 and 2 for now.
4. Small cleanup: don't "restore" EXIT_ZOMBIE unless we know we are not going
to realease the child.
Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Roland McGrath <roland@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 14:26:58 +08:00
|
|
|
int retval, status, traced;
|
2008-02-08 20:19:20 +08:00
|
|
|
pid_t pid = task_pid_vnr(p);
|
2008-11-14 07:39:19 +08:00
|
|
|
uid_t uid = __task_cred(p)->uid;
|
2009-06-18 07:27:39 +08:00
|
|
|
struct siginfo __user *infop;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2009-06-18 07:27:39 +08:00
|
|
|
if (!likely(wo->wo_flags & WEXITED))
|
2008-03-20 10:24:59 +08:00
|
|
|
return 0;
|
|
|
|
|
|
2009-06-18 07:27:39 +08:00
|
|
|
if (unlikely(wo->wo_flags & WNOWAIT)) {
|
2005-04-17 06:20:36 +08:00
|
|
|
int exit_code = p->exit_code;
|
2010-03-06 05:42:52 +08:00
|
|
|
int why;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
get_task_struct(p);
|
|
|
|
|
read_unlock(&tasklist_lock);
|
|
|
|
|
if ((exit_code & 0x7f) == 0) {
|
|
|
|
|
why = CLD_EXITED;
|
|
|
|
|
status = exit_code >> 8;
|
|
|
|
|
} else {
|
|
|
|
|
why = (exit_code & 0x80) ? CLD_DUMPED : CLD_KILLED;
|
|
|
|
|
status = exit_code & 0x7f;
|
|
|
|
|
}
|
2009-06-18 07:27:39 +08:00
|
|
|
return wait_noreap_copyout(wo, p, pid, uid, why, status);
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Try to move the task's state to DEAD
|
|
|
|
|
* only one thread is allowed to do this:
|
|
|
|
|
*/
|
|
|
|
|
state = xchg(&p->exit_state, EXIT_DEAD);
|
|
|
|
|
if (state != EXIT_ZOMBIE) {
|
|
|
|
|
BUG_ON(state != EXIT_DEAD);
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
2008-04-30 15:53:13 +08:00
|
|
|
traced = ptrace_reparented(p);
|
2009-06-19 07:49:11 +08:00
|
|
|
/*
|
|
|
|
|
* It can be ptraced but not reparented, check
|
|
|
|
|
* !task_detached() to filter out sub-threads.
|
|
|
|
|
*/
|
|
|
|
|
if (likely(!traced) && likely(!task_detached(p))) {
|
2006-01-10 12:54:39 +08:00
|
|
|
struct signal_struct *psig;
|
|
|
|
|
struct signal_struct *sig;
|
getrusage: fill ru_maxrss value
Make ->ru_maxrss value in struct rusage filled accordingly to rss hiwater
mark. This struct is filled as a parameter to getrusage syscall.
->ru_maxrss value is set to KBs which is the way it is done in BSD
systems. /usr/bin/time (gnu time) application converts ->ru_maxrss to KBs
which seems to be incorrect behavior. Maintainer of this util was
notified by me with the patch which corrects it and cc'ed.
To make this happen we extend struct signal_struct by two fields. The
first one is ->maxrss which we use to store rss hiwater of the task. The
second one is ->cmaxrss which we use to store highest rss hiwater of all
task childs. These values are used in k_getrusage() to actually fill
->ru_maxrss. k_getrusage() uses current rss hiwater value directly if mm
struct exists.
Note:
exec() clear mm->hiwater_rss, but doesn't clear sig->maxrss.
it is intetionally behavior. *BSD getrusage have exec() inheriting.
test programs
========================================================
getrusage.c
===========
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/types.h>
#include <sys/time.h>
#include <sys/resource.h>
#include <sys/types.h>
#include <sys/wait.h>
#include <unistd.h>
#include <signal.h>
#include <sys/mman.h>
#include "common.h"
#define err(str) perror(str), exit(1)
int main(int argc, char** argv)
{
int status;
printf("allocate 100MB\n");
consume(100);
printf("testcase1: fork inherit? \n");
printf(" expect: initial.self ~= child.self\n");
show_rusage("initial");
if (__fork()) {
wait(&status);
} else {
show_rusage("fork child");
_exit(0);
}
printf("\n");
printf("testcase2: fork inherit? (cont.) \n");
printf(" expect: initial.children ~= 100MB, but child.children = 0\n");
show_rusage("initial");
if (__fork()) {
wait(&status);
} else {
show_rusage("child");
_exit(0);
}
printf("\n");
printf("testcase3: fork + malloc \n");
printf(" expect: child.self ~= initial.self + 50MB\n");
show_rusage("initial");
if (__fork()) {
wait(&status);
} else {
printf("allocate +50MB\n");
consume(50);
show_rusage("fork child");
_exit(0);
}
printf("\n");
printf("testcase4: grandchild maxrss\n");
printf(" expect: post_wait.children ~= 300MB\n");
show_rusage("initial");
if (__fork()) {
wait(&status);
show_rusage("post_wait");
} else {
system("./child -n 0 -g 300");
_exit(0);
}
printf("\n");
printf("testcase5: zombie\n");
printf(" expect: pre_wait ~= initial, IOW the zombie process is not accounted.\n");
printf(" post_wait ~= 400MB, IOW wait() collect child's max_rss. \n");
show_rusage("initial");
if (__fork()) {
sleep(1); /* children become zombie */
show_rusage("pre_wait");
wait(&status);
show_rusage("post_wait");
} else {
system("./child -n 400");
_exit(0);
}
printf("\n");
printf("testcase6: SIG_IGN\n");
printf(" expect: initial ~= after_zombie (child's 500MB alloc should be ignored).\n");
show_rusage("initial");
signal(SIGCHLD, SIG_IGN);
if (__fork()) {
sleep(1); /* children become zombie */
show_rusage("after_zombie");
} else {
system("./child -n 500");
_exit(0);
}
printf("\n");
signal(SIGCHLD, SIG_DFL);
printf("testcase7: exec (without fork) \n");
printf(" expect: initial ~= exec \n");
show_rusage("initial");
execl("./child", "child", "-v", NULL);
return 0;
}
child.c
=======
#include <sys/types.h>
#include <unistd.h>
#include <sys/types.h>
#include <sys/wait.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/types.h>
#include <sys/time.h>
#include <sys/resource.h>
#include "common.h"
int main(int argc, char** argv)
{
int status;
int c;
long consume_size = 0;
long grandchild_consume_size = 0;
int show = 0;
while ((c = getopt(argc, argv, "n:g:v")) != -1) {
switch (c) {
case 'n':
consume_size = atol(optarg);
break;
case 'v':
show = 1;
break;
case 'g':
grandchild_consume_size = atol(optarg);
break;
default:
break;
}
}
if (show)
show_rusage("exec");
if (consume_size) {
printf("child alloc %ldMB\n", consume_size);
consume(consume_size);
}
if (grandchild_consume_size) {
if (fork()) {
wait(&status);
} else {
printf("grandchild alloc %ldMB\n", grandchild_consume_size);
consume(grandchild_consume_size);
exit(0);
}
}
return 0;
}
common.c
========
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/types.h>
#include <sys/time.h>
#include <sys/resource.h>
#include <sys/types.h>
#include <sys/wait.h>
#include <unistd.h>
#include <signal.h>
#include <sys/mman.h>
#include "common.h"
#define err(str) perror(str), exit(1)
void show_rusage(char *prefix)
{
int err, err2;
struct rusage rusage_self;
struct rusage rusage_children;
printf("%s: ", prefix);
err = getrusage(RUSAGE_SELF, &rusage_self);
if (!err)
printf("self %ld ", rusage_self.ru_maxrss);
err2 = getrusage(RUSAGE_CHILDREN, &rusage_children);
if (!err2)
printf("children %ld ", rusage_children.ru_maxrss);
printf("\n");
}
/* Some buggy OS need this worthless CPU waste. */
void make_pagefault(void)
{
void *addr;
int size = getpagesize();
int i;
for (i=0; i<1000; i++) {
addr = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANON, -1, 0);
if (addr == MAP_FAILED)
err("make_pagefault");
memset(addr, 0, size);
munmap(addr, size);
}
}
void consume(int mega)
{
size_t sz = mega * 1024 * 1024;
void *ptr;
ptr = malloc(sz);
memset(ptr, 0, sz);
make_pagefault();
}
pid_t __fork(void)
{
pid_t pid;
pid = fork();
make_pagefault();
return pid;
}
common.h
========
void show_rusage(char *prefix);
void make_pagefault(void);
void consume(int mega);
pid_t __fork(void);
FreeBSD result (expected result)
========================================================
allocate 100MB
testcase1: fork inherit?
expect: initial.self ~= child.self
initial: self 103492 children 0
fork child: self 103540 children 0
testcase2: fork inherit? (cont.)
expect: initial.children ~= 100MB, but child.children = 0
initial: self 103540 children 103540
child: self 103564 children 0
testcase3: fork + malloc
expect: child.self ~= initial.self + 50MB
initial: self 103564 children 103564
allocate +50MB
fork child: self 154860 children 0
testcase4: grandchild maxrss
expect: post_wait.children ~= 300MB
initial: self 103564 children 154860
grandchild alloc 300MB
post_wait: self 103564 children 308720
testcase5: zombie
expect: pre_wait ~= initial, IOW the zombie process is not accounted.
post_wait ~= 400MB, IOW wait() collect child's max_rss.
initial: self 103564 children 308720
child alloc 400MB
pre_wait: self 103564 children 308720
post_wait: self 103564 children 411312
testcase6: SIG_IGN
expect: initial ~= after_zombie (child's 500MB alloc should be ignored).
initial: self 103564 children 411312
child alloc 500MB
after_zombie: self 103624 children 411312
testcase7: exec (without fork)
expect: initial ~= exec
initial: self 103624 children 411312
exec: self 103624 children 411312
Linux result (actual test result)
========================================================
allocate 100MB
testcase1: fork inherit?
expect: initial.self ~= child.self
initial: self 102848 children 0
fork child: self 102572 children 0
testcase2: fork inherit? (cont.)
expect: initial.children ~= 100MB, but child.children = 0
initial: self 102876 children 102644
child: self 102572 children 0
testcase3: fork + malloc
expect: child.self ~= initial.self + 50MB
initial: self 102876 children 102644
allocate +50MB
fork child: self 153804 children 0
testcase4: grandchild maxrss
expect: post_wait.children ~= 300MB
initial: self 102876 children 153864
grandchild alloc 300MB
post_wait: self 102876 children 307536
testcase5: zombie
expect: pre_wait ~= initial, IOW the zombie process is not accounted.
post_wait ~= 400MB, IOW wait() collect child's max_rss.
initial: self 102876 children 307536
child alloc 400MB
pre_wait: self 102876 children 307536
post_wait: self 102876 children 410076
testcase6: SIG_IGN
expect: initial ~= after_zombie (child's 500MB alloc should be ignored).
initial: self 102876 children 410076
child alloc 500MB
after_zombie: self 102880 children 410076
testcase7: exec (without fork)
expect: initial ~= exec
initial: self 102880 children 410076
exec: self 102880 children 410076
Signed-off-by: Jiri Pirko <jpirko@redhat.com>
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Hugh Dickins <hugh.dickins@tiscali.co.uk>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-09-23 07:44:10 +08:00
|
|
|
unsigned long maxrss;
|
sched, cputime: Introduce thread_group_times()
This is a real fix for problem of utime/stime values decreasing
described in the thread:
http://lkml.org/lkml/2009/11/3/522
Now cputime is accounted in the following way:
- {u,s}time in task_struct are increased every time when the thread
is interrupted by a tick (timer interrupt).
- When a thread exits, its {u,s}time are added to signal->{u,s}time,
after adjusted by task_times().
- When all threads in a thread_group exits, accumulated {u,s}time
(and also c{u,s}time) in signal struct are added to c{u,s}time
in signal struct of the group's parent.
So {u,s}time in task struct are "raw" tick count, while
{u,s}time and c{u,s}time in signal struct are "adjusted" values.
And accounted values are used by:
- task_times(), to get cputime of a thread:
This function returns adjusted values that originates from raw
{u,s}time and scaled by sum_exec_runtime that accounted by CFS.
- thread_group_cputime(), to get cputime of a thread group:
This function returns sum of all {u,s}time of living threads in
the group, plus {u,s}time in the signal struct that is sum of
adjusted cputimes of all exited threads belonged to the group.
The problem is the return value of thread_group_cputime(),
because it is mixed sum of "raw" value and "adjusted" value:
group's {u,s}time = foreach(thread){{u,s}time} + exited({u,s}time)
This misbehavior can break {u,s}time monotonicity.
Assume that if there is a thread that have raw values greater
than adjusted values (e.g. interrupted by 1000Hz ticks 50 times
but only runs 45ms) and if it exits, cputime will decrease (e.g.
-5ms).
To fix this, we could do:
group's {u,s}time = foreach(t){task_times(t)} + exited({u,s}time)
But task_times() contains hard divisions, so applying it for
every thread should be avoided.
This patch fixes the above problem in the following way:
- Modify thread's exit (= __exit_signal()) not to use task_times().
It means {u,s}time in signal struct accumulates raw values instead
of adjusted values. As the result it makes thread_group_cputime()
to return pure sum of "raw" values.
- Introduce a new function thread_group_times(*task, *utime, *stime)
that converts "raw" values of thread_group_cputime() to "adjusted"
values, in same calculation procedure as task_times().
- Modify group's exit (= wait_task_zombie()) to use this introduced
thread_group_times(). It make c{u,s}time in signal struct to
have adjusted values like before this patch.
- Replace some thread_group_cputime() by thread_group_times().
This replacements are only applied where conveys the "adjusted"
cputime to users, and where already uses task_times() near by it.
(i.e. sys_times(), getrusage(), and /proc/<PID>/stat.)
This patch have a positive side effect:
- Before this patch, if a group contains many short-life threads
(e.g. runs 0.9ms and not interrupted by ticks), the group's
cputime could be invisible since thread's cputime was accumulated
after adjusted: imagine adjustment function as adj(ticks, runtime),
{adj(0, 0.9) + adj(0, 0.9) + ....} = {0 + 0 + ....} = 0.
After this patch it will not happen because the adjustment is
applied after accumulated.
v2:
- remove if()s, put new variables into signal_struct.
Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: Spencer Candland <spencer@bluehost.com>
Cc: Americo Wang <xiyou.wangcong@gmail.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: Stanislaw Gruszka <sgruszka@redhat.com>
LKML-Reference: <4B162517.8040909@jp.fujitsu.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-02 16:28:07 +08:00
|
|
|
cputime_t tgutime, tgstime;
|
2006-01-10 12:54:39 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/*
|
|
|
|
|
* The resource counters for the group leader are in its
|
|
|
|
|
* own task_struct. Those for dead threads in the group
|
|
|
|
|
* are in its signal_struct, as are those for the child
|
|
|
|
|
* processes it has previously reaped. All these
|
|
|
|
|
* accumulate in the parent's signal_struct c* fields.
|
|
|
|
|
*
|
|
|
|
|
* We don't bother to take a lock here to protect these
|
|
|
|
|
* p->signal fields, because they are only touched by
|
|
|
|
|
* __exit_signal, which runs with tasklist_lock
|
|
|
|
|
* write-locked anyway, and so is excluded here. We do
|
2009-06-18 07:27:34 +08:00
|
|
|
* need to protect the access to parent->signal fields,
|
2005-04-17 06:20:36 +08:00
|
|
|
* as other threads in the parent group can be right
|
|
|
|
|
* here reaping other children at the same time.
|
sched, cputime: Introduce thread_group_times()
This is a real fix for problem of utime/stime values decreasing
described in the thread:
http://lkml.org/lkml/2009/11/3/522
Now cputime is accounted in the following way:
- {u,s}time in task_struct are increased every time when the thread
is interrupted by a tick (timer interrupt).
- When a thread exits, its {u,s}time are added to signal->{u,s}time,
after adjusted by task_times().
- When all threads in a thread_group exits, accumulated {u,s}time
(and also c{u,s}time) in signal struct are added to c{u,s}time
in signal struct of the group's parent.
So {u,s}time in task struct are "raw" tick count, while
{u,s}time and c{u,s}time in signal struct are "adjusted" values.
And accounted values are used by:
- task_times(), to get cputime of a thread:
This function returns adjusted values that originates from raw
{u,s}time and scaled by sum_exec_runtime that accounted by CFS.
- thread_group_cputime(), to get cputime of a thread group:
This function returns sum of all {u,s}time of living threads in
the group, plus {u,s}time in the signal struct that is sum of
adjusted cputimes of all exited threads belonged to the group.
The problem is the return value of thread_group_cputime(),
because it is mixed sum of "raw" value and "adjusted" value:
group's {u,s}time = foreach(thread){{u,s}time} + exited({u,s}time)
This misbehavior can break {u,s}time monotonicity.
Assume that if there is a thread that have raw values greater
than adjusted values (e.g. interrupted by 1000Hz ticks 50 times
but only runs 45ms) and if it exits, cputime will decrease (e.g.
-5ms).
To fix this, we could do:
group's {u,s}time = foreach(t){task_times(t)} + exited({u,s}time)
But task_times() contains hard divisions, so applying it for
every thread should be avoided.
This patch fixes the above problem in the following way:
- Modify thread's exit (= __exit_signal()) not to use task_times().
It means {u,s}time in signal struct accumulates raw values instead
of adjusted values. As the result it makes thread_group_cputime()
to return pure sum of "raw" values.
- Introduce a new function thread_group_times(*task, *utime, *stime)
that converts "raw" values of thread_group_cputime() to "adjusted"
values, in same calculation procedure as task_times().
- Modify group's exit (= wait_task_zombie()) to use this introduced
thread_group_times(). It make c{u,s}time in signal struct to
have adjusted values like before this patch.
- Replace some thread_group_cputime() by thread_group_times().
This replacements are only applied where conveys the "adjusted"
cputime to users, and where already uses task_times() near by it.
(i.e. sys_times(), getrusage(), and /proc/<PID>/stat.)
This patch have a positive side effect:
- Before this patch, if a group contains many short-life threads
(e.g. runs 0.9ms and not interrupted by ticks), the group's
cputime could be invisible since thread's cputime was accumulated
after adjusted: imagine adjustment function as adj(ticks, runtime),
{adj(0, 0.9) + adj(0, 0.9) + ....} = {0 + 0 + ....} = 0.
After this patch it will not happen because the adjustment is
applied after accumulated.
v2:
- remove if()s, put new variables into signal_struct.
Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: Spencer Candland <spencer@bluehost.com>
Cc: Americo Wang <xiyou.wangcong@gmail.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: Stanislaw Gruszka <sgruszka@redhat.com>
LKML-Reference: <4B162517.8040909@jp.fujitsu.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-02 16:28:07 +08:00
|
|
|
*
|
|
|
|
|
* We use thread_group_times() to get times for the thread
|
|
|
|
|
* group, which consolidates times for all threads in the
|
|
|
|
|
* group including the group leader.
|
2005-04-17 06:20:36 +08:00
|
|
|
*/
|
sched, cputime: Introduce thread_group_times()
This is a real fix for problem of utime/stime values decreasing
described in the thread:
http://lkml.org/lkml/2009/11/3/522
Now cputime is accounted in the following way:
- {u,s}time in task_struct are increased every time when the thread
is interrupted by a tick (timer interrupt).
- When a thread exits, its {u,s}time are added to signal->{u,s}time,
after adjusted by task_times().
- When all threads in a thread_group exits, accumulated {u,s}time
(and also c{u,s}time) in signal struct are added to c{u,s}time
in signal struct of the group's parent.
So {u,s}time in task struct are "raw" tick count, while
{u,s}time and c{u,s}time in signal struct are "adjusted" values.
And accounted values are used by:
- task_times(), to get cputime of a thread:
This function returns adjusted values that originates from raw
{u,s}time and scaled by sum_exec_runtime that accounted by CFS.
- thread_group_cputime(), to get cputime of a thread group:
This function returns sum of all {u,s}time of living threads in
the group, plus {u,s}time in the signal struct that is sum of
adjusted cputimes of all exited threads belonged to the group.
The problem is the return value of thread_group_cputime(),
because it is mixed sum of "raw" value and "adjusted" value:
group's {u,s}time = foreach(thread){{u,s}time} + exited({u,s}time)
This misbehavior can break {u,s}time monotonicity.
Assume that if there is a thread that have raw values greater
than adjusted values (e.g. interrupted by 1000Hz ticks 50 times
but only runs 45ms) and if it exits, cputime will decrease (e.g.
-5ms).
To fix this, we could do:
group's {u,s}time = foreach(t){task_times(t)} + exited({u,s}time)
But task_times() contains hard divisions, so applying it for
every thread should be avoided.
This patch fixes the above problem in the following way:
- Modify thread's exit (= __exit_signal()) not to use task_times().
It means {u,s}time in signal struct accumulates raw values instead
of adjusted values. As the result it makes thread_group_cputime()
to return pure sum of "raw" values.
- Introduce a new function thread_group_times(*task, *utime, *stime)
that converts "raw" values of thread_group_cputime() to "adjusted"
values, in same calculation procedure as task_times().
- Modify group's exit (= wait_task_zombie()) to use this introduced
thread_group_times(). It make c{u,s}time in signal struct to
have adjusted values like before this patch.
- Replace some thread_group_cputime() by thread_group_times().
This replacements are only applied where conveys the "adjusted"
cputime to users, and where already uses task_times() near by it.
(i.e. sys_times(), getrusage(), and /proc/<PID>/stat.)
This patch have a positive side effect:
- Before this patch, if a group contains many short-life threads
(e.g. runs 0.9ms and not interrupted by ticks), the group's
cputime could be invisible since thread's cputime was accumulated
after adjusted: imagine adjustment function as adj(ticks, runtime),
{adj(0, 0.9) + adj(0, 0.9) + ....} = {0 + 0 + ....} = 0.
After this patch it will not happen because the adjustment is
applied after accumulated.
v2:
- remove if()s, put new variables into signal_struct.
Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: Spencer Candland <spencer@bluehost.com>
Cc: Americo Wang <xiyou.wangcong@gmail.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: Stanislaw Gruszka <sgruszka@redhat.com>
LKML-Reference: <4B162517.8040909@jp.fujitsu.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-02 16:28:07 +08:00
|
|
|
thread_group_times(p, &tgutime, &tgstime);
|
2009-06-18 07:27:34 +08:00
|
|
|
spin_lock_irq(&p->real_parent->sighand->siglock);
|
|
|
|
|
psig = p->real_parent->signal;
|
2006-01-10 12:54:39 +08:00
|
|
|
sig = p->signal;
|
|
|
|
|
psig->cutime =
|
|
|
|
|
cputime_add(psig->cutime,
|
sched, cputime: Introduce thread_group_times()
This is a real fix for problem of utime/stime values decreasing
described in the thread:
http://lkml.org/lkml/2009/11/3/522
Now cputime is accounted in the following way:
- {u,s}time in task_struct are increased every time when the thread
is interrupted by a tick (timer interrupt).
- When a thread exits, its {u,s}time are added to signal->{u,s}time,
after adjusted by task_times().
- When all threads in a thread_group exits, accumulated {u,s}time
(and also c{u,s}time) in signal struct are added to c{u,s}time
in signal struct of the group's parent.
So {u,s}time in task struct are "raw" tick count, while
{u,s}time and c{u,s}time in signal struct are "adjusted" values.
And accounted values are used by:
- task_times(), to get cputime of a thread:
This function returns adjusted values that originates from raw
{u,s}time and scaled by sum_exec_runtime that accounted by CFS.
- thread_group_cputime(), to get cputime of a thread group:
This function returns sum of all {u,s}time of living threads in
the group, plus {u,s}time in the signal struct that is sum of
adjusted cputimes of all exited threads belonged to the group.
The problem is the return value of thread_group_cputime(),
because it is mixed sum of "raw" value and "adjusted" value:
group's {u,s}time = foreach(thread){{u,s}time} + exited({u,s}time)
This misbehavior can break {u,s}time monotonicity.
Assume that if there is a thread that have raw values greater
than adjusted values (e.g. interrupted by 1000Hz ticks 50 times
but only runs 45ms) and if it exits, cputime will decrease (e.g.
-5ms).
To fix this, we could do:
group's {u,s}time = foreach(t){task_times(t)} + exited({u,s}time)
But task_times() contains hard divisions, so applying it for
every thread should be avoided.
This patch fixes the above problem in the following way:
- Modify thread's exit (= __exit_signal()) not to use task_times().
It means {u,s}time in signal struct accumulates raw values instead
of adjusted values. As the result it makes thread_group_cputime()
to return pure sum of "raw" values.
- Introduce a new function thread_group_times(*task, *utime, *stime)
that converts "raw" values of thread_group_cputime() to "adjusted"
values, in same calculation procedure as task_times().
- Modify group's exit (= wait_task_zombie()) to use this introduced
thread_group_times(). It make c{u,s}time in signal struct to
have adjusted values like before this patch.
- Replace some thread_group_cputime() by thread_group_times().
This replacements are only applied where conveys the "adjusted"
cputime to users, and where already uses task_times() near by it.
(i.e. sys_times(), getrusage(), and /proc/<PID>/stat.)
This patch have a positive side effect:
- Before this patch, if a group contains many short-life threads
(e.g. runs 0.9ms and not interrupted by ticks), the group's
cputime could be invisible since thread's cputime was accumulated
after adjusted: imagine adjustment function as adj(ticks, runtime),
{adj(0, 0.9) + adj(0, 0.9) + ....} = {0 + 0 + ....} = 0.
After this patch it will not happen because the adjustment is
applied after accumulated.
v2:
- remove if()s, put new variables into signal_struct.
Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: Spencer Candland <spencer@bluehost.com>
Cc: Americo Wang <xiyou.wangcong@gmail.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: Stanislaw Gruszka <sgruszka@redhat.com>
LKML-Reference: <4B162517.8040909@jp.fujitsu.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-02 16:28:07 +08:00
|
|
|
cputime_add(tgutime,
|
|
|
|
|
sig->cutime));
|
2006-01-10 12:54:39 +08:00
|
|
|
psig->cstime =
|
|
|
|
|
cputime_add(psig->cstime,
|
sched, cputime: Introduce thread_group_times()
This is a real fix for problem of utime/stime values decreasing
described in the thread:
http://lkml.org/lkml/2009/11/3/522
Now cputime is accounted in the following way:
- {u,s}time in task_struct are increased every time when the thread
is interrupted by a tick (timer interrupt).
- When a thread exits, its {u,s}time are added to signal->{u,s}time,
after adjusted by task_times().
- When all threads in a thread_group exits, accumulated {u,s}time
(and also c{u,s}time) in signal struct are added to c{u,s}time
in signal struct of the group's parent.
So {u,s}time in task struct are "raw" tick count, while
{u,s}time and c{u,s}time in signal struct are "adjusted" values.
And accounted values are used by:
- task_times(), to get cputime of a thread:
This function returns adjusted values that originates from raw
{u,s}time and scaled by sum_exec_runtime that accounted by CFS.
- thread_group_cputime(), to get cputime of a thread group:
This function returns sum of all {u,s}time of living threads in
the group, plus {u,s}time in the signal struct that is sum of
adjusted cputimes of all exited threads belonged to the group.
The problem is the return value of thread_group_cputime(),
because it is mixed sum of "raw" value and "adjusted" value:
group's {u,s}time = foreach(thread){{u,s}time} + exited({u,s}time)
This misbehavior can break {u,s}time monotonicity.
Assume that if there is a thread that have raw values greater
than adjusted values (e.g. interrupted by 1000Hz ticks 50 times
but only runs 45ms) and if it exits, cputime will decrease (e.g.
-5ms).
To fix this, we could do:
group's {u,s}time = foreach(t){task_times(t)} + exited({u,s}time)
But task_times() contains hard divisions, so applying it for
every thread should be avoided.
This patch fixes the above problem in the following way:
- Modify thread's exit (= __exit_signal()) not to use task_times().
It means {u,s}time in signal struct accumulates raw values instead
of adjusted values. As the result it makes thread_group_cputime()
to return pure sum of "raw" values.
- Introduce a new function thread_group_times(*task, *utime, *stime)
that converts "raw" values of thread_group_cputime() to "adjusted"
values, in same calculation procedure as task_times().
- Modify group's exit (= wait_task_zombie()) to use this introduced
thread_group_times(). It make c{u,s}time in signal struct to
have adjusted values like before this patch.
- Replace some thread_group_cputime() by thread_group_times().
This replacements are only applied where conveys the "adjusted"
cputime to users, and where already uses task_times() near by it.
(i.e. sys_times(), getrusage(), and /proc/<PID>/stat.)
This patch have a positive side effect:
- Before this patch, if a group contains many short-life threads
(e.g. runs 0.9ms and not interrupted by ticks), the group's
cputime could be invisible since thread's cputime was accumulated
after adjusted: imagine adjustment function as adj(ticks, runtime),
{adj(0, 0.9) + adj(0, 0.9) + ....} = {0 + 0 + ....} = 0.
After this patch it will not happen because the adjustment is
applied after accumulated.
v2:
- remove if()s, put new variables into signal_struct.
Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: Spencer Candland <spencer@bluehost.com>
Cc: Americo Wang <xiyou.wangcong@gmail.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: Stanislaw Gruszka <sgruszka@redhat.com>
LKML-Reference: <4B162517.8040909@jp.fujitsu.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-02 16:28:07 +08:00
|
|
|
cputime_add(tgstime,
|
|
|
|
|
sig->cstime));
|
2007-10-15 23:00:19 +08:00
|
|
|
psig->cgtime =
|
|
|
|
|
cputime_add(psig->cgtime,
|
|
|
|
|
cputime_add(p->gtime,
|
|
|
|
|
cputime_add(sig->gtime,
|
|
|
|
|
sig->cgtime)));
|
2006-01-10 12:54:39 +08:00
|
|
|
psig->cmin_flt +=
|
|
|
|
|
p->min_flt + sig->min_flt + sig->cmin_flt;
|
|
|
|
|
psig->cmaj_flt +=
|
|
|
|
|
p->maj_flt + sig->maj_flt + sig->cmaj_flt;
|
|
|
|
|
psig->cnvcsw +=
|
|
|
|
|
p->nvcsw + sig->nvcsw + sig->cnvcsw;
|
|
|
|
|
psig->cnivcsw +=
|
|
|
|
|
p->nivcsw + sig->nivcsw + sig->cnivcsw;
|
2007-05-11 13:22:37 +08:00
|
|
|
psig->cinblock +=
|
|
|
|
|
task_io_get_inblock(p) +
|
|
|
|
|
sig->inblock + sig->cinblock;
|
|
|
|
|
psig->coublock +=
|
|
|
|
|
task_io_get_oublock(p) +
|
|
|
|
|
sig->oublock + sig->coublock;
|
getrusage: fill ru_maxrss value
Make ->ru_maxrss value in struct rusage filled accordingly to rss hiwater
mark. This struct is filled as a parameter to getrusage syscall.
->ru_maxrss value is set to KBs which is the way it is done in BSD
systems. /usr/bin/time (gnu time) application converts ->ru_maxrss to KBs
which seems to be incorrect behavior. Maintainer of this util was
notified by me with the patch which corrects it and cc'ed.
To make this happen we extend struct signal_struct by two fields. The
first one is ->maxrss which we use to store rss hiwater of the task. The
second one is ->cmaxrss which we use to store highest rss hiwater of all
task childs. These values are used in k_getrusage() to actually fill
->ru_maxrss. k_getrusage() uses current rss hiwater value directly if mm
struct exists.
Note:
exec() clear mm->hiwater_rss, but doesn't clear sig->maxrss.
it is intetionally behavior. *BSD getrusage have exec() inheriting.
test programs
========================================================
getrusage.c
===========
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/types.h>
#include <sys/time.h>
#include <sys/resource.h>
#include <sys/types.h>
#include <sys/wait.h>
#include <unistd.h>
#include <signal.h>
#include <sys/mman.h>
#include "common.h"
#define err(str) perror(str), exit(1)
int main(int argc, char** argv)
{
int status;
printf("allocate 100MB\n");
consume(100);
printf("testcase1: fork inherit? \n");
printf(" expect: initial.self ~= child.self\n");
show_rusage("initial");
if (__fork()) {
wait(&status);
} else {
show_rusage("fork child");
_exit(0);
}
printf("\n");
printf("testcase2: fork inherit? (cont.) \n");
printf(" expect: initial.children ~= 100MB, but child.children = 0\n");
show_rusage("initial");
if (__fork()) {
wait(&status);
} else {
show_rusage("child");
_exit(0);
}
printf("\n");
printf("testcase3: fork + malloc \n");
printf(" expect: child.self ~= initial.self + 50MB\n");
show_rusage("initial");
if (__fork()) {
wait(&status);
} else {
printf("allocate +50MB\n");
consume(50);
show_rusage("fork child");
_exit(0);
}
printf("\n");
printf("testcase4: grandchild maxrss\n");
printf(" expect: post_wait.children ~= 300MB\n");
show_rusage("initial");
if (__fork()) {
wait(&status);
show_rusage("post_wait");
} else {
system("./child -n 0 -g 300");
_exit(0);
}
printf("\n");
printf("testcase5: zombie\n");
printf(" expect: pre_wait ~= initial, IOW the zombie process is not accounted.\n");
printf(" post_wait ~= 400MB, IOW wait() collect child's max_rss. \n");
show_rusage("initial");
if (__fork()) {
sleep(1); /* children become zombie */
show_rusage("pre_wait");
wait(&status);
show_rusage("post_wait");
} else {
system("./child -n 400");
_exit(0);
}
printf("\n");
printf("testcase6: SIG_IGN\n");
printf(" expect: initial ~= after_zombie (child's 500MB alloc should be ignored).\n");
show_rusage("initial");
signal(SIGCHLD, SIG_IGN);
if (__fork()) {
sleep(1); /* children become zombie */
show_rusage("after_zombie");
} else {
system("./child -n 500");
_exit(0);
}
printf("\n");
signal(SIGCHLD, SIG_DFL);
printf("testcase7: exec (without fork) \n");
printf(" expect: initial ~= exec \n");
show_rusage("initial");
execl("./child", "child", "-v", NULL);
return 0;
}
child.c
=======
#include <sys/types.h>
#include <unistd.h>
#include <sys/types.h>
#include <sys/wait.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/types.h>
#include <sys/time.h>
#include <sys/resource.h>
#include "common.h"
int main(int argc, char** argv)
{
int status;
int c;
long consume_size = 0;
long grandchild_consume_size = 0;
int show = 0;
while ((c = getopt(argc, argv, "n:g:v")) != -1) {
switch (c) {
case 'n':
consume_size = atol(optarg);
break;
case 'v':
show = 1;
break;
case 'g':
grandchild_consume_size = atol(optarg);
break;
default:
break;
}
}
if (show)
show_rusage("exec");
if (consume_size) {
printf("child alloc %ldMB\n", consume_size);
consume(consume_size);
}
if (grandchild_consume_size) {
if (fork()) {
wait(&status);
} else {
printf("grandchild alloc %ldMB\n", grandchild_consume_size);
consume(grandchild_consume_size);
exit(0);
}
}
return 0;
}
common.c
========
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/types.h>
#include <sys/time.h>
#include <sys/resource.h>
#include <sys/types.h>
#include <sys/wait.h>
#include <unistd.h>
#include <signal.h>
#include <sys/mman.h>
#include "common.h"
#define err(str) perror(str), exit(1)
void show_rusage(char *prefix)
{
int err, err2;
struct rusage rusage_self;
struct rusage rusage_children;
printf("%s: ", prefix);
err = getrusage(RUSAGE_SELF, &rusage_self);
if (!err)
printf("self %ld ", rusage_self.ru_maxrss);
err2 = getrusage(RUSAGE_CHILDREN, &rusage_children);
if (!err2)
printf("children %ld ", rusage_children.ru_maxrss);
printf("\n");
}
/* Some buggy OS need this worthless CPU waste. */
void make_pagefault(void)
{
void *addr;
int size = getpagesize();
int i;
for (i=0; i<1000; i++) {
addr = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANON, -1, 0);
if (addr == MAP_FAILED)
err("make_pagefault");
memset(addr, 0, size);
munmap(addr, size);
}
}
void consume(int mega)
{
size_t sz = mega * 1024 * 1024;
void *ptr;
ptr = malloc(sz);
memset(ptr, 0, sz);
make_pagefault();
}
pid_t __fork(void)
{
pid_t pid;
pid = fork();
make_pagefault();
return pid;
}
common.h
========
void show_rusage(char *prefix);
void make_pagefault(void);
void consume(int mega);
pid_t __fork(void);
FreeBSD result (expected result)
========================================================
allocate 100MB
testcase1: fork inherit?
expect: initial.self ~= child.self
initial: self 103492 children 0
fork child: self 103540 children 0
testcase2: fork inherit? (cont.)
expect: initial.children ~= 100MB, but child.children = 0
initial: self 103540 children 103540
child: self 103564 children 0
testcase3: fork + malloc
expect: child.self ~= initial.self + 50MB
initial: self 103564 children 103564
allocate +50MB
fork child: self 154860 children 0
testcase4: grandchild maxrss
expect: post_wait.children ~= 300MB
initial: self 103564 children 154860
grandchild alloc 300MB
post_wait: self 103564 children 308720
testcase5: zombie
expect: pre_wait ~= initial, IOW the zombie process is not accounted.
post_wait ~= 400MB, IOW wait() collect child's max_rss.
initial: self 103564 children 308720
child alloc 400MB
pre_wait: self 103564 children 308720
post_wait: self 103564 children 411312
testcase6: SIG_IGN
expect: initial ~= after_zombie (child's 500MB alloc should be ignored).
initial: self 103564 children 411312
child alloc 500MB
after_zombie: self 103624 children 411312
testcase7: exec (without fork)
expect: initial ~= exec
initial: self 103624 children 411312
exec: self 103624 children 411312
Linux result (actual test result)
========================================================
allocate 100MB
testcase1: fork inherit?
expect: initial.self ~= child.self
initial: self 102848 children 0
fork child: self 102572 children 0
testcase2: fork inherit? (cont.)
expect: initial.children ~= 100MB, but child.children = 0
initial: self 102876 children 102644
child: self 102572 children 0
testcase3: fork + malloc
expect: child.self ~= initial.self + 50MB
initial: self 102876 children 102644
allocate +50MB
fork child: self 153804 children 0
testcase4: grandchild maxrss
expect: post_wait.children ~= 300MB
initial: self 102876 children 153864
grandchild alloc 300MB
post_wait: self 102876 children 307536
testcase5: zombie
expect: pre_wait ~= initial, IOW the zombie process is not accounted.
post_wait ~= 400MB, IOW wait() collect child's max_rss.
initial: self 102876 children 307536
child alloc 400MB
pre_wait: self 102876 children 307536
post_wait: self 102876 children 410076
testcase6: SIG_IGN
expect: initial ~= after_zombie (child's 500MB alloc should be ignored).
initial: self 102876 children 410076
child alloc 500MB
after_zombie: self 102880 children 410076
testcase7: exec (without fork)
expect: initial ~= exec
initial: self 102880 children 410076
exec: self 102880 children 410076
Signed-off-by: Jiri Pirko <jpirko@redhat.com>
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Hugh Dickins <hugh.dickins@tiscali.co.uk>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-09-23 07:44:10 +08:00
|
|
|
maxrss = max(sig->maxrss, sig->cmaxrss);
|
|
|
|
|
if (psig->cmaxrss < maxrss)
|
|
|
|
|
psig->cmaxrss = maxrss;
|
2008-07-27 23:29:15 +08:00
|
|
|
task_io_accounting_add(&psig->ioac, &p->ioac);
|
|
|
|
|
task_io_accounting_add(&psig->ioac, &sig->ioac);
|
2009-06-18 07:27:34 +08:00
|
|
|
spin_unlock_irq(&p->real_parent->sighand->siglock);
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Now we are sure this task is interesting, and no other
|
|
|
|
|
* thread can reap it because we set its state to EXIT_DEAD.
|
|
|
|
|
*/
|
|
|
|
|
read_unlock(&tasklist_lock);
|
|
|
|
|
|
2009-06-18 07:27:39 +08:00
|
|
|
retval = wo->wo_rusage
|
|
|
|
|
? getrusage(p, RUSAGE_BOTH, wo->wo_rusage) : 0;
|
2005-04-17 06:20:36 +08:00
|
|
|
status = (p->signal->flags & SIGNAL_GROUP_EXIT)
|
|
|
|
|
? p->signal->group_exit_code : p->exit_code;
|
2009-06-18 07:27:39 +08:00
|
|
|
if (!retval && wo->wo_stat)
|
|
|
|
|
retval = put_user(status, wo->wo_stat);
|
|
|
|
|
|
|
|
|
|
infop = wo->wo_info;
|
2005-04-17 06:20:36 +08:00
|
|
|
if (!retval && infop)
|
|
|
|
|
retval = put_user(SIGCHLD, &infop->si_signo);
|
|
|
|
|
if (!retval && infop)
|
|
|
|
|
retval = put_user(0, &infop->si_errno);
|
|
|
|
|
if (!retval && infop) {
|
|
|
|
|
int why;
|
|
|
|
|
|
|
|
|
|
if ((status & 0x7f) == 0) {
|
|
|
|
|
why = CLD_EXITED;
|
|
|
|
|
status >>= 8;
|
|
|
|
|
} else {
|
|
|
|
|
why = (status & 0x80) ? CLD_DUMPED : CLD_KILLED;
|
|
|
|
|
status &= 0x7f;
|
|
|
|
|
}
|
|
|
|
|
retval = put_user((short)why, &infop->si_code);
|
|
|
|
|
if (!retval)
|
|
|
|
|
retval = put_user(status, &infop->si_status);
|
|
|
|
|
}
|
|
|
|
|
if (!retval && infop)
|
2008-02-08 20:19:07 +08:00
|
|
|
retval = put_user(pid, &infop->si_pid);
|
2005-04-17 06:20:36 +08:00
|
|
|
if (!retval && infop)
|
2008-11-14 07:39:19 +08:00
|
|
|
retval = put_user(uid, &infop->si_uid);
|
wait_task_zombie: fix 2/3 races vs forget_original_parent()
Two threads, T1 and T2. T2 ptraces P, and P is not a child of ptracer's
thread group. P exits and goes to TASK_ZOMBIE.
T1 does wait_task_zombie(P):
P->exit_state = TASK_DEAD;
...
read_unlock(&tasklist_lock);
T2 does exit(), takes tasklist,
forget_original_parent() does
__ptrace_unlink(P) but doesn't
call do_notify_parent(P) because
p->exit_state == EXIT_DEAD.
Now, P is not visible to our process: __ptrace_unlink() removed it from
->children. We should send notification to P->parent and release P if and
only if SIGCHLD is ignored.
And we have 3 bugs:
1. P->parent does do_wait() and gets -ECHILD (P is on ->parent->children,
but its state is TASK_DEAD).
2. // wait_task_zombie() continues
if (put_user(...)) {
// TODO: is this safe?
p->exit_state = EXIT_ZOMBIE;
return;
}
we return without notification/release, task_struct leaked.
Solution: ignore -EFAULT and proceed. It is an application's bug if
we can't fill infop/stat_addr (in case of VM_FAULT_OOM we have much
more problems).
3. // wait_task_zombie() continues
if (p->real_parent != p->parent) {
// Not taken, it was untraced'ed
...
}
release_task(p);
we released the task which we shouldn't.
Solution: check ->real_parent != ->parent before, under tasklist_lock,
but use ptrace_unlink() instead of __ptrace_unlink() to check ->ptrace.
This patch hopefully solves 2 and 3, the 1st bug will be fixed later, we need
some cleanups in forget_original_parent/reparent_thread.
However, the first race is very unlikely and not critical, so I hope it makes
sense to fix 1 and 2 for now.
4. Small cleanup: don't "restore" EXIT_ZOMBIE unless we know we are not going
to realease the child.
Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Roland McGrath <roland@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 14:26:58 +08:00
|
|
|
if (!retval)
|
2008-02-08 20:19:07 +08:00
|
|
|
retval = pid;
|
wait_task_zombie: fix 2/3 races vs forget_original_parent()
Two threads, T1 and T2. T2 ptraces P, and P is not a child of ptracer's
thread group. P exits and goes to TASK_ZOMBIE.
T1 does wait_task_zombie(P):
P->exit_state = TASK_DEAD;
...
read_unlock(&tasklist_lock);
T2 does exit(), takes tasklist,
forget_original_parent() does
__ptrace_unlink(P) but doesn't
call do_notify_parent(P) because
p->exit_state == EXIT_DEAD.
Now, P is not visible to our process: __ptrace_unlink() removed it from
->children. We should send notification to P->parent and release P if and
only if SIGCHLD is ignored.
And we have 3 bugs:
1. P->parent does do_wait() and gets -ECHILD (P is on ->parent->children,
but its state is TASK_DEAD).
2. // wait_task_zombie() continues
if (put_user(...)) {
// TODO: is this safe?
p->exit_state = EXIT_ZOMBIE;
return;
}
we return without notification/release, task_struct leaked.
Solution: ignore -EFAULT and proceed. It is an application's bug if
we can't fill infop/stat_addr (in case of VM_FAULT_OOM we have much
more problems).
3. // wait_task_zombie() continues
if (p->real_parent != p->parent) {
// Not taken, it was untraced'ed
...
}
release_task(p);
we released the task which we shouldn't.
Solution: check ->real_parent != ->parent before, under tasklist_lock,
but use ptrace_unlink() instead of __ptrace_unlink() to check ->ptrace.
This patch hopefully solves 2 and 3, the 1st bug will be fixed later, we need
some cleanups in forget_original_parent/reparent_thread.
However, the first race is very unlikely and not critical, so I hope it makes
sense to fix 1 and 2 for now.
4. Small cleanup: don't "restore" EXIT_ZOMBIE unless we know we are not going
to realease the child.
Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Roland McGrath <roland@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 14:26:58 +08:00
|
|
|
|
|
|
|
|
if (traced) {
|
2005-04-17 06:20:36 +08:00
|
|
|
write_lock_irq(&tasklist_lock);
|
wait_task_zombie: fix 2/3 races vs forget_original_parent()
Two threads, T1 and T2. T2 ptraces P, and P is not a child of ptracer's
thread group. P exits and goes to TASK_ZOMBIE.
T1 does wait_task_zombie(P):
P->exit_state = TASK_DEAD;
...
read_unlock(&tasklist_lock);
T2 does exit(), takes tasklist,
forget_original_parent() does
__ptrace_unlink(P) but doesn't
call do_notify_parent(P) because
p->exit_state == EXIT_DEAD.
Now, P is not visible to our process: __ptrace_unlink() removed it from
->children. We should send notification to P->parent and release P if and
only if SIGCHLD is ignored.
And we have 3 bugs:
1. P->parent does do_wait() and gets -ECHILD (P is on ->parent->children,
but its state is TASK_DEAD).
2. // wait_task_zombie() continues
if (put_user(...)) {
// TODO: is this safe?
p->exit_state = EXIT_ZOMBIE;
return;
}
we return without notification/release, task_struct leaked.
Solution: ignore -EFAULT and proceed. It is an application's bug if
we can't fill infop/stat_addr (in case of VM_FAULT_OOM we have much
more problems).
3. // wait_task_zombie() continues
if (p->real_parent != p->parent) {
// Not taken, it was untraced'ed
...
}
release_task(p);
we released the task which we shouldn't.
Solution: check ->real_parent != ->parent before, under tasklist_lock,
but use ptrace_unlink() instead of __ptrace_unlink() to check ->ptrace.
This patch hopefully solves 2 and 3, the 1st bug will be fixed later, we need
some cleanups in forget_original_parent/reparent_thread.
However, the first race is very unlikely and not critical, so I hope it makes
sense to fix 1 and 2 for now.
4. Small cleanup: don't "restore" EXIT_ZOMBIE unless we know we are not going
to realease the child.
Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Roland McGrath <roland@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 14:26:58 +08:00
|
|
|
/* We dropped tasklist, ptracer could die and untrace */
|
|
|
|
|
ptrace_unlink(p);
|
|
|
|
|
/*
|
|
|
|
|
* If this is not a detached task, notify the parent.
|
|
|
|
|
* If it's still not detached after that, don't release
|
|
|
|
|
* it now.
|
|
|
|
|
*/
|
2008-04-30 15:53:11 +08:00
|
|
|
if (!task_detached(p)) {
|
wait_task_zombie: fix 2/3 races vs forget_original_parent()
Two threads, T1 and T2. T2 ptraces P, and P is not a child of ptracer's
thread group. P exits and goes to TASK_ZOMBIE.
T1 does wait_task_zombie(P):
P->exit_state = TASK_DEAD;
...
read_unlock(&tasklist_lock);
T2 does exit(), takes tasklist,
forget_original_parent() does
__ptrace_unlink(P) but doesn't
call do_notify_parent(P) because
p->exit_state == EXIT_DEAD.
Now, P is not visible to our process: __ptrace_unlink() removed it from
->children. We should send notification to P->parent and release P if and
only if SIGCHLD is ignored.
And we have 3 bugs:
1. P->parent does do_wait() and gets -ECHILD (P is on ->parent->children,
but its state is TASK_DEAD).
2. // wait_task_zombie() continues
if (put_user(...)) {
// TODO: is this safe?
p->exit_state = EXIT_ZOMBIE;
return;
}
we return without notification/release, task_struct leaked.
Solution: ignore -EFAULT and proceed. It is an application's bug if
we can't fill infop/stat_addr (in case of VM_FAULT_OOM we have much
more problems).
3. // wait_task_zombie() continues
if (p->real_parent != p->parent) {
// Not taken, it was untraced'ed
...
}
release_task(p);
we released the task which we shouldn't.
Solution: check ->real_parent != ->parent before, under tasklist_lock,
but use ptrace_unlink() instead of __ptrace_unlink() to check ->ptrace.
This patch hopefully solves 2 and 3, the 1st bug will be fixed later, we need
some cleanups in forget_original_parent/reparent_thread.
However, the first race is very unlikely and not critical, so I hope it makes
sense to fix 1 and 2 for now.
4. Small cleanup: don't "restore" EXIT_ZOMBIE unless we know we are not going
to realease the child.
Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Roland McGrath <roland@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 14:26:58 +08:00
|
|
|
do_notify_parent(p, p->exit_signal);
|
2008-04-30 15:53:11 +08:00
|
|
|
if (!task_detached(p)) {
|
wait_task_zombie: fix 2/3 races vs forget_original_parent()
Two threads, T1 and T2. T2 ptraces P, and P is not a child of ptracer's
thread group. P exits and goes to TASK_ZOMBIE.
T1 does wait_task_zombie(P):
P->exit_state = TASK_DEAD;
...
read_unlock(&tasklist_lock);
T2 does exit(), takes tasklist,
forget_original_parent() does
__ptrace_unlink(P) but doesn't
call do_notify_parent(P) because
p->exit_state == EXIT_DEAD.
Now, P is not visible to our process: __ptrace_unlink() removed it from
->children. We should send notification to P->parent and release P if and
only if SIGCHLD is ignored.
And we have 3 bugs:
1. P->parent does do_wait() and gets -ECHILD (P is on ->parent->children,
but its state is TASK_DEAD).
2. // wait_task_zombie() continues
if (put_user(...)) {
// TODO: is this safe?
p->exit_state = EXIT_ZOMBIE;
return;
}
we return without notification/release, task_struct leaked.
Solution: ignore -EFAULT and proceed. It is an application's bug if
we can't fill infop/stat_addr (in case of VM_FAULT_OOM we have much
more problems).
3. // wait_task_zombie() continues
if (p->real_parent != p->parent) {
// Not taken, it was untraced'ed
...
}
release_task(p);
we released the task which we shouldn't.
Solution: check ->real_parent != ->parent before, under tasklist_lock,
but use ptrace_unlink() instead of __ptrace_unlink() to check ->ptrace.
This patch hopefully solves 2 and 3, the 1st bug will be fixed later, we need
some cleanups in forget_original_parent/reparent_thread.
However, the first race is very unlikely and not critical, so I hope it makes
sense to fix 1 and 2 for now.
4. Small cleanup: don't "restore" EXIT_ZOMBIE unless we know we are not going
to realease the child.
Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Roland McGrath <roland@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 14:26:58 +08:00
|
|
|
p->exit_state = EXIT_ZOMBIE;
|
|
|
|
|
p = NULL;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
write_unlock_irq(&tasklist_lock);
|
|
|
|
|
}
|
|
|
|
|
if (p != NULL)
|
|
|
|
|
release_task(p);
|
wait_task_zombie: fix 2/3 races vs forget_original_parent()
Two threads, T1 and T2. T2 ptraces P, and P is not a child of ptracer's
thread group. P exits and goes to TASK_ZOMBIE.
T1 does wait_task_zombie(P):
P->exit_state = TASK_DEAD;
...
read_unlock(&tasklist_lock);
T2 does exit(), takes tasklist,
forget_original_parent() does
__ptrace_unlink(P) but doesn't
call do_notify_parent(P) because
p->exit_state == EXIT_DEAD.
Now, P is not visible to our process: __ptrace_unlink() removed it from
->children. We should send notification to P->parent and release P if and
only if SIGCHLD is ignored.
And we have 3 bugs:
1. P->parent does do_wait() and gets -ECHILD (P is on ->parent->children,
but its state is TASK_DEAD).
2. // wait_task_zombie() continues
if (put_user(...)) {
// TODO: is this safe?
p->exit_state = EXIT_ZOMBIE;
return;
}
we return without notification/release, task_struct leaked.
Solution: ignore -EFAULT and proceed. It is an application's bug if
we can't fill infop/stat_addr (in case of VM_FAULT_OOM we have much
more problems).
3. // wait_task_zombie() continues
if (p->real_parent != p->parent) {
// Not taken, it was untraced'ed
...
}
release_task(p);
we released the task which we shouldn't.
Solution: check ->real_parent != ->parent before, under tasklist_lock,
but use ptrace_unlink() instead of __ptrace_unlink() to check ->ptrace.
This patch hopefully solves 2 and 3, the 1st bug will be fixed later, we need
some cleanups in forget_original_parent/reparent_thread.
However, the first race is very unlikely and not critical, so I hope it makes
sense to fix 1 and 2 for now.
4. Small cleanup: don't "restore" EXIT_ZOMBIE unless we know we are not going
to realease the child.
Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Roland McGrath <roland@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 14:26:58 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
return retval;
|
|
|
|
|
}
|
|
|
|
|
|
do_wait: fix waiting for the group stop with the dead leader
do_wait(WSTOPPED) assumes that p->state must be == TASK_STOPPED, this is
not true if the leader is already dead. Check SIGNAL_STOP_STOPPED instead
and use signal->group_exit_code.
Trivial test-case:
void *tfunc(void *arg)
{
pause();
return NULL;
}
int main(void)
{
pthread_t thr;
pthread_create(&thr, NULL, tfunc, NULL);
pthread_exit(NULL);
return 0;
}
It doesn't react to ^Z (and then to ^C or ^\). The task is stopped, but
bash can't see this.
The bug is very old, and it was reported multiple times. This patch was sent
more than a year ago (http://marc.info/?t=119713920000003) but it was ignored.
This change also fixes other oddities (but not all) in this area. For
example, before this patch:
$ sleep 100
^Z
[1]+ Stopped sleep 100
$ strace -p `pidof sleep`
Process 11442 attached - interrupt to quit
strace hangs in do_wait(), because ->exit_code was already consumed by
bash. After this patch, strace happily proceeds:
--- SIGTSTP (Stopped) @ 0 (0) ---
restart_syscall(<... resuming interrupted call ...>
To me, this looks much more "natural" and correct.
Another example. Let's suppose we have the main thread M and sub-thread
T, the process is stopped, and its parent did wait(WSTOPPED). Now we can
ptrace T but not M. This looks at least strange to me.
Imho, do_wait() should not confuse the per-thread ptrace stops with the
per-process job control stops.
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Jan Kratochvil <jan.kratochvil@redhat.com>
Cc: Kaz Kylheku <kkylheku@gmail.com>
Cc: Michael Kerrisk <mtk.manpages@googlemail.com>
Cc: Roland McGrath <roland@redhat.com>
Cc: Ulrich Drepper <drepper@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-03 07:57:58 +08:00
|
|
|
static int *task_stopped_code(struct task_struct *p, bool ptrace)
|
|
|
|
|
{
|
|
|
|
|
if (ptrace) {
|
|
|
|
|
if (task_is_stopped_or_traced(p))
|
|
|
|
|
return &p->exit_code;
|
|
|
|
|
} else {
|
|
|
|
|
if (p->signal->flags & SIGNAL_STOP_STOPPED)
|
|
|
|
|
return &p->signal->group_exit_code;
|
|
|
|
|
}
|
|
|
|
|
return NULL;
|
|
|
|
|
}
|
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/*
|
|
|
|
|
* Handle sys_wait4 work for one task in state TASK_STOPPED. We hold
|
|
|
|
|
* read_lock(&tasklist_lock) on entry. If we return zero, we still hold
|
|
|
|
|
* the lock and this task is uninteresting. If we return nonzero, we have
|
|
|
|
|
* released the lock and the system call should return.
|
|
|
|
|
*/
|
2009-06-18 07:27:39 +08:00
|
|
|
static int wait_task_stopped(struct wait_opts *wo,
|
|
|
|
|
int ptrace, struct task_struct *p)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2009-06-18 07:27:39 +08:00
|
|
|
struct siginfo __user *infop;
|
do_wait: fix waiting for the group stop with the dead leader
do_wait(WSTOPPED) assumes that p->state must be == TASK_STOPPED, this is
not true if the leader is already dead. Check SIGNAL_STOP_STOPPED instead
and use signal->group_exit_code.
Trivial test-case:
void *tfunc(void *arg)
{
pause();
return NULL;
}
int main(void)
{
pthread_t thr;
pthread_create(&thr, NULL, tfunc, NULL);
pthread_exit(NULL);
return 0;
}
It doesn't react to ^Z (and then to ^C or ^\). The task is stopped, but
bash can't see this.
The bug is very old, and it was reported multiple times. This patch was sent
more than a year ago (http://marc.info/?t=119713920000003) but it was ignored.
This change also fixes other oddities (but not all) in this area. For
example, before this patch:
$ sleep 100
^Z
[1]+ Stopped sleep 100
$ strace -p `pidof sleep`
Process 11442 attached - interrupt to quit
strace hangs in do_wait(), because ->exit_code was already consumed by
bash. After this patch, strace happily proceeds:
--- SIGTSTP (Stopped) @ 0 (0) ---
restart_syscall(<... resuming interrupted call ...>
To me, this looks much more "natural" and correct.
Another example. Let's suppose we have the main thread M and sub-thread
T, the process is stopped, and its parent did wait(WSTOPPED). Now we can
ptrace T but not M. This looks at least strange to me.
Imho, do_wait() should not confuse the per-thread ptrace stops with the
per-process job control stops.
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Jan Kratochvil <jan.kratochvil@redhat.com>
Cc: Kaz Kylheku <kkylheku@gmail.com>
Cc: Michael Kerrisk <mtk.manpages@googlemail.com>
Cc: Roland McGrath <roland@redhat.com>
Cc: Ulrich Drepper <drepper@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-03 07:57:58 +08:00
|
|
|
int retval, exit_code, *p_code, why;
|
2008-02-08 20:19:01 +08:00
|
|
|
uid_t uid = 0; /* unneeded, required by compiler */
|
2007-11-29 08:21:24 +08:00
|
|
|
pid_t pid;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2009-06-18 07:27:39 +08:00
|
|
|
/*
|
|
|
|
|
* Traditionally we see ptrace'd stopped tasks regardless of options.
|
|
|
|
|
*/
|
2009-06-18 07:27:39 +08:00
|
|
|
if (!ptrace && !(wo->wo_flags & WUNTRACED))
|
2008-03-20 10:24:59 +08:00
|
|
|
return 0;
|
|
|
|
|
|
2008-02-08 20:19:01 +08:00
|
|
|
exit_code = 0;
|
|
|
|
|
spin_lock_irq(&p->sighand->siglock);
|
|
|
|
|
|
do_wait: fix waiting for the group stop with the dead leader
do_wait(WSTOPPED) assumes that p->state must be == TASK_STOPPED, this is
not true if the leader is already dead. Check SIGNAL_STOP_STOPPED instead
and use signal->group_exit_code.
Trivial test-case:
void *tfunc(void *arg)
{
pause();
return NULL;
}
int main(void)
{
pthread_t thr;
pthread_create(&thr, NULL, tfunc, NULL);
pthread_exit(NULL);
return 0;
}
It doesn't react to ^Z (and then to ^C or ^\). The task is stopped, but
bash can't see this.
The bug is very old, and it was reported multiple times. This patch was sent
more than a year ago (http://marc.info/?t=119713920000003) but it was ignored.
This change also fixes other oddities (but not all) in this area. For
example, before this patch:
$ sleep 100
^Z
[1]+ Stopped sleep 100
$ strace -p `pidof sleep`
Process 11442 attached - interrupt to quit
strace hangs in do_wait(), because ->exit_code was already consumed by
bash. After this patch, strace happily proceeds:
--- SIGTSTP (Stopped) @ 0 (0) ---
restart_syscall(<... resuming interrupted call ...>
To me, this looks much more "natural" and correct.
Another example. Let's suppose we have the main thread M and sub-thread
T, the process is stopped, and its parent did wait(WSTOPPED). Now we can
ptrace T but not M. This looks at least strange to me.
Imho, do_wait() should not confuse the per-thread ptrace stops with the
per-process job control stops.
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Jan Kratochvil <jan.kratochvil@redhat.com>
Cc: Kaz Kylheku <kkylheku@gmail.com>
Cc: Michael Kerrisk <mtk.manpages@googlemail.com>
Cc: Roland McGrath <roland@redhat.com>
Cc: Ulrich Drepper <drepper@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-03 07:57:58 +08:00
|
|
|
p_code = task_stopped_code(p, ptrace);
|
|
|
|
|
if (unlikely(!p_code))
|
2008-02-08 20:19:01 +08:00
|
|
|
goto unlock_sig;
|
|
|
|
|
|
do_wait: fix waiting for the group stop with the dead leader
do_wait(WSTOPPED) assumes that p->state must be == TASK_STOPPED, this is
not true if the leader is already dead. Check SIGNAL_STOP_STOPPED instead
and use signal->group_exit_code.
Trivial test-case:
void *tfunc(void *arg)
{
pause();
return NULL;
}
int main(void)
{
pthread_t thr;
pthread_create(&thr, NULL, tfunc, NULL);
pthread_exit(NULL);
return 0;
}
It doesn't react to ^Z (and then to ^C or ^\). The task is stopped, but
bash can't see this.
The bug is very old, and it was reported multiple times. This patch was sent
more than a year ago (http://marc.info/?t=119713920000003) but it was ignored.
This change also fixes other oddities (but not all) in this area. For
example, before this patch:
$ sleep 100
^Z
[1]+ Stopped sleep 100
$ strace -p `pidof sleep`
Process 11442 attached - interrupt to quit
strace hangs in do_wait(), because ->exit_code was already consumed by
bash. After this patch, strace happily proceeds:
--- SIGTSTP (Stopped) @ 0 (0) ---
restart_syscall(<... resuming interrupted call ...>
To me, this looks much more "natural" and correct.
Another example. Let's suppose we have the main thread M and sub-thread
T, the process is stopped, and its parent did wait(WSTOPPED). Now we can
ptrace T but not M. This looks at least strange to me.
Imho, do_wait() should not confuse the per-thread ptrace stops with the
per-process job control stops.
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Jan Kratochvil <jan.kratochvil@redhat.com>
Cc: Kaz Kylheku <kkylheku@gmail.com>
Cc: Michael Kerrisk <mtk.manpages@googlemail.com>
Cc: Roland McGrath <roland@redhat.com>
Cc: Ulrich Drepper <drepper@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-03 07:57:58 +08:00
|
|
|
exit_code = *p_code;
|
2008-02-08 20:19:01 +08:00
|
|
|
if (!exit_code)
|
|
|
|
|
goto unlock_sig;
|
|
|
|
|
|
2009-06-18 07:27:39 +08:00
|
|
|
if (!unlikely(wo->wo_flags & WNOWAIT))
|
do_wait: fix waiting for the group stop with the dead leader
do_wait(WSTOPPED) assumes that p->state must be == TASK_STOPPED, this is
not true if the leader is already dead. Check SIGNAL_STOP_STOPPED instead
and use signal->group_exit_code.
Trivial test-case:
void *tfunc(void *arg)
{
pause();
return NULL;
}
int main(void)
{
pthread_t thr;
pthread_create(&thr, NULL, tfunc, NULL);
pthread_exit(NULL);
return 0;
}
It doesn't react to ^Z (and then to ^C or ^\). The task is stopped, but
bash can't see this.
The bug is very old, and it was reported multiple times. This patch was sent
more than a year ago (http://marc.info/?t=119713920000003) but it was ignored.
This change also fixes other oddities (but not all) in this area. For
example, before this patch:
$ sleep 100
^Z
[1]+ Stopped sleep 100
$ strace -p `pidof sleep`
Process 11442 attached - interrupt to quit
strace hangs in do_wait(), because ->exit_code was already consumed by
bash. After this patch, strace happily proceeds:
--- SIGTSTP (Stopped) @ 0 (0) ---
restart_syscall(<... resuming interrupted call ...>
To me, this looks much more "natural" and correct.
Another example. Let's suppose we have the main thread M and sub-thread
T, the process is stopped, and its parent did wait(WSTOPPED). Now we can
ptrace T but not M. This looks at least strange to me.
Imho, do_wait() should not confuse the per-thread ptrace stops with the
per-process job control stops.
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Jan Kratochvil <jan.kratochvil@redhat.com>
Cc: Kaz Kylheku <kkylheku@gmail.com>
Cc: Michael Kerrisk <mtk.manpages@googlemail.com>
Cc: Roland McGrath <roland@redhat.com>
Cc: Ulrich Drepper <drepper@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-03 07:57:58 +08:00
|
|
|
*p_code = 0;
|
2008-02-08 20:19:01 +08:00
|
|
|
|
Fix unprotected access to task credentials in waitid()
Using a program like the following:
#include <stdlib.h>
#include <unistd.h>
#include <sys/types.h>
#include <sys/wait.h>
int main() {
id_t id;
siginfo_t infop;
pid_t res;
id = fork();
if (id == 0) { sleep(1); exit(0); }
kill(id, SIGSTOP);
alarm(1);
waitid(P_PID, id, &infop, WCONTINUED);
return 0;
}
to call waitid() on a stopped process results in access to the child task's
credentials without the RCU read lock being held - which may be replaced in the
meantime - eliciting the following warning:
===================================================
[ INFO: suspicious rcu_dereference_check() usage. ]
---------------------------------------------------
kernel/exit.c:1460 invoked rcu_dereference_check() without protection!
other info that might help us debug this:
rcu_scheduler_active = 1, debug_locks = 1
2 locks held by waitid02/22252:
#0: (tasklist_lock){.?.?..}, at: [<ffffffff81061ce5>] do_wait+0xc5/0x310
#1: (&(&sighand->siglock)->rlock){-.-...}, at: [<ffffffff810611da>]
wait_consider_task+0x19a/0xbe0
stack backtrace:
Pid: 22252, comm: waitid02 Not tainted 2.6.35-323cd+ #3
Call Trace:
[<ffffffff81095da4>] lockdep_rcu_dereference+0xa4/0xc0
[<ffffffff81061b31>] wait_consider_task+0xaf1/0xbe0
[<ffffffff81061d15>] do_wait+0xf5/0x310
[<ffffffff810620b6>] sys_waitid+0x86/0x1f0
[<ffffffff8105fce0>] ? child_wait_callback+0x0/0x70
[<ffffffff81003282>] system_call_fastpath+0x16/0x1b
This is fixed by holding the RCU read lock in wait_task_continued() to ensure
that the task's current credentials aren't destroyed between us reading the
cred pointer and us reading the UID from those credentials.
Furthermore, protect wait_task_stopped() in the same way.
We don't need to keep holding the RCU read lock once we've read the UID from
the credentials as holding the RCU read lock doesn't stop the target task from
changing its creds under us - so the credentials may be outdated immediately
after we've read the pointer, lock or no lock.
Signed-off-by: Daniel J Blueman <daniel.blueman@gmail.com>
Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Acked-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-08-18 06:56:55 +08:00
|
|
|
uid = task_uid(p);
|
2008-02-08 20:19:01 +08:00
|
|
|
unlock_sig:
|
|
|
|
|
spin_unlock_irq(&p->sighand->siglock);
|
|
|
|
|
if (!exit_code)
|
2005-04-17 06:20:36 +08:00
|
|
|
return 0;
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Now we are pretty sure this task is interesting.
|
|
|
|
|
* Make sure it doesn't get reaped out from under us while we
|
|
|
|
|
* give up the lock and then examine it below. We don't want to
|
|
|
|
|
* keep holding onto the tasklist_lock while we call getrusage and
|
|
|
|
|
* possibly take page faults for user memory.
|
|
|
|
|
*/
|
|
|
|
|
get_task_struct(p);
|
2008-02-08 20:19:20 +08:00
|
|
|
pid = task_pid_vnr(p);
|
2008-03-25 09:36:23 +08:00
|
|
|
why = ptrace ? CLD_TRAPPED : CLD_STOPPED;
|
2005-04-17 06:20:36 +08:00
|
|
|
read_unlock(&tasklist_lock);
|
|
|
|
|
|
2009-06-18 07:27:39 +08:00
|
|
|
if (unlikely(wo->wo_flags & WNOWAIT))
|
|
|
|
|
return wait_noreap_copyout(wo, p, pid, uid, why, exit_code);
|
|
|
|
|
|
|
|
|
|
retval = wo->wo_rusage
|
|
|
|
|
? getrusage(p, RUSAGE_BOTH, wo->wo_rusage) : 0;
|
|
|
|
|
if (!retval && wo->wo_stat)
|
|
|
|
|
retval = put_user((exit_code << 8) | 0x7f, wo->wo_stat);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2009-06-18 07:27:39 +08:00
|
|
|
infop = wo->wo_info;
|
2005-04-17 06:20:36 +08:00
|
|
|
if (!retval && infop)
|
|
|
|
|
retval = put_user(SIGCHLD, &infop->si_signo);
|
|
|
|
|
if (!retval && infop)
|
|
|
|
|
retval = put_user(0, &infop->si_errno);
|
|
|
|
|
if (!retval && infop)
|
2008-03-09 03:41:22 +08:00
|
|
|
retval = put_user((short)why, &infop->si_code);
|
2005-04-17 06:20:36 +08:00
|
|
|
if (!retval && infop)
|
|
|
|
|
retval = put_user(exit_code, &infop->si_status);
|
|
|
|
|
if (!retval && infop)
|
2007-11-29 08:21:24 +08:00
|
|
|
retval = put_user(pid, &infop->si_pid);
|
2005-04-17 06:20:36 +08:00
|
|
|
if (!retval && infop)
|
2008-02-08 20:19:01 +08:00
|
|
|
retval = put_user(uid, &infop->si_uid);
|
2005-04-17 06:20:36 +08:00
|
|
|
if (!retval)
|
2007-11-29 08:21:24 +08:00
|
|
|
retval = pid;
|
2005-04-17 06:20:36 +08:00
|
|
|
put_task_struct(p);
|
|
|
|
|
|
|
|
|
|
BUG_ON(!retval);
|
|
|
|
|
return retval;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Handle do_wait work for one task in a live, non-stopped state.
|
|
|
|
|
* read_lock(&tasklist_lock) on entry. If we return zero, we still hold
|
|
|
|
|
* the lock and this task is uninteresting. If we return nonzero, we have
|
|
|
|
|
* released the lock and the system call should return.
|
|
|
|
|
*/
|
2009-06-18 07:27:39 +08:00
|
|
|
static int wait_task_continued(struct wait_opts *wo, struct task_struct *p)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
|
int retval;
|
|
|
|
|
pid_t pid;
|
|
|
|
|
uid_t uid;
|
|
|
|
|
|
2009-06-18 07:27:39 +08:00
|
|
|
if (!unlikely(wo->wo_flags & WCONTINUED))
|
2008-03-20 10:24:59 +08:00
|
|
|
return 0;
|
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
if (!(p->signal->flags & SIGNAL_STOP_CONTINUED))
|
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
|
|
spin_lock_irq(&p->sighand->siglock);
|
|
|
|
|
/* Re-check with the lock held. */
|
|
|
|
|
if (!(p->signal->flags & SIGNAL_STOP_CONTINUED)) {
|
|
|
|
|
spin_unlock_irq(&p->sighand->siglock);
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
2009-06-18 07:27:39 +08:00
|
|
|
if (!unlikely(wo->wo_flags & WNOWAIT))
|
2005-04-17 06:20:36 +08:00
|
|
|
p->signal->flags &= ~SIGNAL_STOP_CONTINUED;
|
Fix unprotected access to task credentials in waitid()
Using a program like the following:
#include <stdlib.h>
#include <unistd.h>
#include <sys/types.h>
#include <sys/wait.h>
int main() {
id_t id;
siginfo_t infop;
pid_t res;
id = fork();
if (id == 0) { sleep(1); exit(0); }
kill(id, SIGSTOP);
alarm(1);
waitid(P_PID, id, &infop, WCONTINUED);
return 0;
}
to call waitid() on a stopped process results in access to the child task's
credentials without the RCU read lock being held - which may be replaced in the
meantime - eliciting the following warning:
===================================================
[ INFO: suspicious rcu_dereference_check() usage. ]
---------------------------------------------------
kernel/exit.c:1460 invoked rcu_dereference_check() without protection!
other info that might help us debug this:
rcu_scheduler_active = 1, debug_locks = 1
2 locks held by waitid02/22252:
#0: (tasklist_lock){.?.?..}, at: [<ffffffff81061ce5>] do_wait+0xc5/0x310
#1: (&(&sighand->siglock)->rlock){-.-...}, at: [<ffffffff810611da>]
wait_consider_task+0x19a/0xbe0
stack backtrace:
Pid: 22252, comm: waitid02 Not tainted 2.6.35-323cd+ #3
Call Trace:
[<ffffffff81095da4>] lockdep_rcu_dereference+0xa4/0xc0
[<ffffffff81061b31>] wait_consider_task+0xaf1/0xbe0
[<ffffffff81061d15>] do_wait+0xf5/0x310
[<ffffffff810620b6>] sys_waitid+0x86/0x1f0
[<ffffffff8105fce0>] ? child_wait_callback+0x0/0x70
[<ffffffff81003282>] system_call_fastpath+0x16/0x1b
This is fixed by holding the RCU read lock in wait_task_continued() to ensure
that the task's current credentials aren't destroyed between us reading the
cred pointer and us reading the UID from those credentials.
Furthermore, protect wait_task_stopped() in the same way.
We don't need to keep holding the RCU read lock once we've read the UID from
the credentials as holding the RCU read lock doesn't stop the target task from
changing its creds under us - so the credentials may be outdated immediately
after we've read the pointer, lock or no lock.
Signed-off-by: Daniel J Blueman <daniel.blueman@gmail.com>
Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Acked-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-08-18 06:56:55 +08:00
|
|
|
uid = task_uid(p);
|
2005-04-17 06:20:36 +08:00
|
|
|
spin_unlock_irq(&p->sighand->siglock);
|
|
|
|
|
|
2008-02-08 20:19:20 +08:00
|
|
|
pid = task_pid_vnr(p);
|
2005-04-17 06:20:36 +08:00
|
|
|
get_task_struct(p);
|
|
|
|
|
read_unlock(&tasklist_lock);
|
|
|
|
|
|
2009-06-18 07:27:39 +08:00
|
|
|
if (!wo->wo_info) {
|
|
|
|
|
retval = wo->wo_rusage
|
|
|
|
|
? getrusage(p, RUSAGE_BOTH, wo->wo_rusage) : 0;
|
2005-04-17 06:20:36 +08:00
|
|
|
put_task_struct(p);
|
2009-06-18 07:27:39 +08:00
|
|
|
if (!retval && wo->wo_stat)
|
|
|
|
|
retval = put_user(0xffff, wo->wo_stat);
|
2005-04-17 06:20:36 +08:00
|
|
|
if (!retval)
|
2008-02-08 20:19:07 +08:00
|
|
|
retval = pid;
|
2005-04-17 06:20:36 +08:00
|
|
|
} else {
|
2009-06-18 07:27:39 +08:00
|
|
|
retval = wait_noreap_copyout(wo, p, pid, uid,
|
|
|
|
|
CLD_CONTINUED, SIGCONT);
|
2005-04-17 06:20:36 +08:00
|
|
|
BUG_ON(retval == 0);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
return retval;
|
|
|
|
|
}
|
|
|
|
|
|
2008-03-20 10:24:59 +08:00
|
|
|
/*
|
|
|
|
|
* Consider @p for a wait by @parent.
|
|
|
|
|
*
|
2009-06-18 07:27:39 +08:00
|
|
|
* -ECHILD should be in ->notask_error before the first call.
|
2008-03-20 10:24:59 +08:00
|
|
|
* Returns nonzero for a final return, when we have unlocked tasklist_lock.
|
|
|
|
|
* Returns zero if the search for a child should continue;
|
2009-06-18 07:27:39 +08:00
|
|
|
* then ->notask_error is 0 if @p is an eligible child,
|
2008-03-31 09:41:25 +08:00
|
|
|
* or another error from security_task_wait(), or still -ECHILD.
|
2008-03-20 10:24:59 +08:00
|
|
|
*/
|
2009-09-24 06:56:50 +08:00
|
|
|
static int wait_consider_task(struct wait_opts *wo, int ptrace,
|
|
|
|
|
struct task_struct *p)
|
2008-03-20 10:24:59 +08:00
|
|
|
{
|
2009-06-18 07:27:39 +08:00
|
|
|
int ret = eligible_child(wo, p);
|
2008-03-31 09:41:25 +08:00
|
|
|
if (!ret)
|
2008-03-20 10:24:59 +08:00
|
|
|
return ret;
|
|
|
|
|
|
2009-09-24 06:56:45 +08:00
|
|
|
ret = security_task_wait(p);
|
2008-03-31 09:41:25 +08:00
|
|
|
if (unlikely(ret < 0)) {
|
|
|
|
|
/*
|
|
|
|
|
* If we have not yet seen any eligible child,
|
|
|
|
|
* then let this error code replace -ECHILD.
|
|
|
|
|
* A permission error will give the user a clue
|
|
|
|
|
* to look for security policy problems, rather
|
|
|
|
|
* than for mysterious wait bugs.
|
|
|
|
|
*/
|
2009-06-18 07:27:39 +08:00
|
|
|
if (wo->notask_error)
|
|
|
|
|
wo->notask_error = ret;
|
2009-04-30 00:01:23 +08:00
|
|
|
return 0;
|
2008-03-31 09:41:25 +08:00
|
|
|
}
|
|
|
|
|
|
2009-06-18 07:27:30 +08:00
|
|
|
if (likely(!ptrace) && unlikely(task_ptrace(p))) {
|
2008-03-25 09:36:23 +08:00
|
|
|
/*
|
|
|
|
|
* This child is hidden by ptrace.
|
|
|
|
|
* We aren't allowed to see it now, but eventually we will.
|
|
|
|
|
*/
|
2009-06-18 07:27:39 +08:00
|
|
|
wo->notask_error = 0;
|
2008-03-25 09:36:23 +08:00
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
2008-03-20 10:24:59 +08:00
|
|
|
if (p->exit_state == EXIT_DEAD)
|
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* We don't reap group leaders with subthreads.
|
|
|
|
|
*/
|
|
|
|
|
if (p->exit_state == EXIT_ZOMBIE && !delay_group_leader(p))
|
2009-06-18 07:27:39 +08:00
|
|
|
return wait_task_zombie(wo, p);
|
2008-03-20 10:24:59 +08:00
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* It's stopped or running now, so it might
|
|
|
|
|
* later continue, exit, or stop again.
|
|
|
|
|
*/
|
2009-06-18 07:27:39 +08:00
|
|
|
wo->notask_error = 0;
|
2008-03-20 10:24:59 +08:00
|
|
|
|
do_wait: fix waiting for the group stop with the dead leader
do_wait(WSTOPPED) assumes that p->state must be == TASK_STOPPED, this is
not true if the leader is already dead. Check SIGNAL_STOP_STOPPED instead
and use signal->group_exit_code.
Trivial test-case:
void *tfunc(void *arg)
{
pause();
return NULL;
}
int main(void)
{
pthread_t thr;
pthread_create(&thr, NULL, tfunc, NULL);
pthread_exit(NULL);
return 0;
}
It doesn't react to ^Z (and then to ^C or ^\). The task is stopped, but
bash can't see this.
The bug is very old, and it was reported multiple times. This patch was sent
more than a year ago (http://marc.info/?t=119713920000003) but it was ignored.
This change also fixes other oddities (but not all) in this area. For
example, before this patch:
$ sleep 100
^Z
[1]+ Stopped sleep 100
$ strace -p `pidof sleep`
Process 11442 attached - interrupt to quit
strace hangs in do_wait(), because ->exit_code was already consumed by
bash. After this patch, strace happily proceeds:
--- SIGTSTP (Stopped) @ 0 (0) ---
restart_syscall(<... resuming interrupted call ...>
To me, this looks much more "natural" and correct.
Another example. Let's suppose we have the main thread M and sub-thread
T, the process is stopped, and its parent did wait(WSTOPPED). Now we can
ptrace T but not M. This looks at least strange to me.
Imho, do_wait() should not confuse the per-thread ptrace stops with the
per-process job control stops.
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Jan Kratochvil <jan.kratochvil@redhat.com>
Cc: Kaz Kylheku <kkylheku@gmail.com>
Cc: Michael Kerrisk <mtk.manpages@googlemail.com>
Cc: Roland McGrath <roland@redhat.com>
Cc: Ulrich Drepper <drepper@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-03 07:57:58 +08:00
|
|
|
if (task_stopped_code(p, ptrace))
|
2009-06-18 07:27:39 +08:00
|
|
|
return wait_task_stopped(wo, ptrace, p);
|
2008-03-20 10:24:59 +08:00
|
|
|
|
2009-06-18 07:27:39 +08:00
|
|
|
return wait_task_continued(wo, p);
|
2008-03-20 10:24:59 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Do the work of do_wait() for one thread in the group, @tsk.
|
|
|
|
|
*
|
2009-06-18 07:27:39 +08:00
|
|
|
* -ECHILD should be in ->notask_error before the first call.
|
2008-03-20 10:24:59 +08:00
|
|
|
* Returns nonzero for a final return, when we have unlocked tasklist_lock.
|
|
|
|
|
* Returns zero if the search for a child should continue; then
|
2009-06-18 07:27:39 +08:00
|
|
|
* ->notask_error is 0 if there were any eligible children,
|
2008-03-31 09:41:25 +08:00
|
|
|
* or another error from security_task_wait(), or still -ECHILD.
|
2008-03-20 10:24:59 +08:00
|
|
|
*/
|
2009-06-18 07:27:39 +08:00
|
|
|
static int do_wait_thread(struct wait_opts *wo, struct task_struct *tsk)
|
2008-03-20 10:24:59 +08:00
|
|
|
{
|
|
|
|
|
struct task_struct *p;
|
|
|
|
|
|
|
|
|
|
list_for_each_entry(p, &tsk->children, sibling) {
|
2009-12-18 07:27:15 +08:00
|
|
|
int ret = wait_consider_task(wo, 0, p);
|
|
|
|
|
if (ret)
|
|
|
|
|
return ret;
|
2008-03-20 10:24:59 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
2009-06-18 07:27:39 +08:00
|
|
|
static int ptrace_do_wait(struct wait_opts *wo, struct task_struct *tsk)
|
2008-03-20 10:24:59 +08:00
|
|
|
{
|
|
|
|
|
struct task_struct *p;
|
|
|
|
|
|
2008-03-25 09:36:23 +08:00
|
|
|
list_for_each_entry(p, &tsk->ptraced, ptrace_entry) {
|
2009-09-24 06:56:50 +08:00
|
|
|
int ret = wait_consider_task(wo, 1, p);
|
2008-03-25 09:36:23 +08:00
|
|
|
if (ret)
|
2008-03-20 10:24:59 +08:00
|
|
|
return ret;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
2009-09-24 06:56:46 +08:00
|
|
|
static int child_wait_callback(wait_queue_t *wait, unsigned mode,
|
|
|
|
|
int sync, void *key)
|
|
|
|
|
{
|
|
|
|
|
struct wait_opts *wo = container_of(wait, struct wait_opts,
|
|
|
|
|
child_wait);
|
|
|
|
|
struct task_struct *p = key;
|
|
|
|
|
|
2009-09-24 06:56:48 +08:00
|
|
|
if (!eligible_pid(wo, p))
|
2009-09-24 06:56:46 +08:00
|
|
|
return 0;
|
|
|
|
|
|
2009-09-24 06:56:47 +08:00
|
|
|
if ((wo->wo_flags & __WNOTHREAD) && wait->private != p->parent)
|
|
|
|
|
return 0;
|
|
|
|
|
|
2009-09-24 06:56:46 +08:00
|
|
|
return default_wake_function(wait, mode, sync, key);
|
|
|
|
|
}
|
|
|
|
|
|
ptrace: __ptrace_detach: do __wake_up_parent() if we reap the tracee
The bug is old, it wasn't cause by recent changes.
Test case:
static void *tfunc(void *arg)
{
int pid = (long)arg;
assert(ptrace(PTRACE_ATTACH, pid, NULL, NULL) == 0);
kill(pid, SIGKILL);
sleep(1);
return NULL;
}
int main(void)
{
pthread_t th;
long pid = fork();
if (!pid)
pause();
signal(SIGCHLD, SIG_IGN);
assert(pthread_create(&th, NULL, tfunc, (void*)pid) == 0);
int r = waitpid(-1, NULL, __WNOTHREAD);
printf("waitpid: %d %m\n", r);
return 0;
}
Before the patch this program hangs, after this patch waitpid() correctly
fails with errno == -ECHILD.
The problem is, __ptrace_detach() reaps the EXIT_ZOMBIE tracee if its
->real_parent is our sub-thread and we ignore SIGCHLD. But in this case
we should wake up other threads which can sleep in do_wait().
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Cc: Roland McGrath <roland@redhat.com>
Cc: Vitaly Mayatskikh <vmayatsk@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-09-24 06:56:44 +08:00
|
|
|
void __wake_up_parent(struct task_struct *p, struct task_struct *parent)
|
|
|
|
|
{
|
2009-09-24 06:56:46 +08:00
|
|
|
__wake_up_sync_key(&parent->signal->wait_chldexit,
|
|
|
|
|
TASK_INTERRUPTIBLE, 1, p);
|
ptrace: __ptrace_detach: do __wake_up_parent() if we reap the tracee
The bug is old, it wasn't cause by recent changes.
Test case:
static void *tfunc(void *arg)
{
int pid = (long)arg;
assert(ptrace(PTRACE_ATTACH, pid, NULL, NULL) == 0);
kill(pid, SIGKILL);
sleep(1);
return NULL;
}
int main(void)
{
pthread_t th;
long pid = fork();
if (!pid)
pause();
signal(SIGCHLD, SIG_IGN);
assert(pthread_create(&th, NULL, tfunc, (void*)pid) == 0);
int r = waitpid(-1, NULL, __WNOTHREAD);
printf("waitpid: %d %m\n", r);
return 0;
}
Before the patch this program hangs, after this patch waitpid() correctly
fails with errno == -ECHILD.
The problem is, __ptrace_detach() reaps the EXIT_ZOMBIE tracee if its
->real_parent is our sub-thread and we ignore SIGCHLD. But in this case
we should wake up other threads which can sleep in do_wait().
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Cc: Roland McGrath <roland@redhat.com>
Cc: Vitaly Mayatskikh <vmayatsk@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-09-24 06:56:44 +08:00
|
|
|
}
|
|
|
|
|
|
2009-06-18 07:27:39 +08:00
|
|
|
static long do_wait(struct wait_opts *wo)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
|
struct task_struct *tsk;
|
2008-03-20 10:24:59 +08:00
|
|
|
int retval;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2009-06-18 07:27:39 +08:00
|
|
|
trace_sched_process_wait(wo->wo_pid);
|
tracing, sched: LTTng instrumentation - scheduler
Instrument the scheduler activity (sched_switch, migration, wakeups,
wait for a task, signal delivery) and process/thread
creation/destruction (fork, exit, kthread stop). Actually, kthread
creation is not instrumented in this patch because it is architecture
dependent. It allows to connect tracers such as ftrace which detects
scheduling latencies, good/bad scheduler decisions. Tools like LTTng can
export this scheduler information along with instrumentation of the rest
of the kernel activity to perform post-mortem analysis on the scheduler
activity.
About the performance impact of tracepoints (which is comparable to
markers), even without immediate values optimizations, tests done by
Hideo Aoki on ia64 show no regression. His test case was using hackbench
on a kernel where scheduler instrumentation (about 5 events in code
scheduler code) was added. See the "Tracepoints" patch header for
performance result detail.
Changelog :
- Change instrumentation location and parameter to match ftrace
instrumentation, previously done with kernel markers.
[ mingo@elte.hu: conflict resolutions ]
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
Acked-by: 'Peter Zijlstra' <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-07-19 00:16:17 +08:00
|
|
|
|
2009-09-24 06:56:46 +08:00
|
|
|
init_waitqueue_func_entry(&wo->child_wait, child_wait_callback);
|
|
|
|
|
wo->child_wait.private = current;
|
|
|
|
|
add_wait_queue(¤t->signal->wait_chldexit, &wo->child_wait);
|
2005-04-17 06:20:36 +08:00
|
|
|
repeat:
|
2008-03-20 10:24:59 +08:00
|
|
|
/*
|
|
|
|
|
* If there is nothing that can match our critiera just get out.
|
2009-06-18 07:27:39 +08:00
|
|
|
* We will clear ->notask_error to zero if we see any child that
|
|
|
|
|
* might later match our criteria, even if we are not able to reap
|
|
|
|
|
* it yet.
|
2008-03-20 10:24:59 +08:00
|
|
|
*/
|
2009-06-18 07:27:40 +08:00
|
|
|
wo->notask_error = -ECHILD;
|
2009-06-18 07:27:39 +08:00
|
|
|
if ((wo->wo_type < PIDTYPE_MAX) &&
|
|
|
|
|
(!wo->wo_pid || hlist_empty(&wo->wo_pid->tasks[wo->wo_type])))
|
2009-06-18 07:27:40 +08:00
|
|
|
goto notask;
|
2008-02-08 20:19:14 +08:00
|
|
|
|
2009-06-18 07:27:42 +08:00
|
|
|
set_current_state(TASK_INTERRUPTIBLE);
|
2005-04-17 06:20:36 +08:00
|
|
|
read_lock(&tasklist_lock);
|
|
|
|
|
tsk = current;
|
|
|
|
|
do {
|
2009-06-18 07:27:40 +08:00
|
|
|
retval = do_wait_thread(wo, tsk);
|
|
|
|
|
if (retval)
|
|
|
|
|
goto end;
|
2009-06-18 07:27:39 +08:00
|
|
|
|
2009-06-18 07:27:40 +08:00
|
|
|
retval = ptrace_do_wait(wo, tsk);
|
|
|
|
|
if (retval)
|
2008-03-20 10:24:59 +08:00
|
|
|
goto end;
|
|
|
|
|
|
2009-06-18 07:27:39 +08:00
|
|
|
if (wo->wo_flags & __WNOTHREAD)
|
2005-04-17 06:20:36 +08:00
|
|
|
break;
|
2009-06-18 07:27:41 +08:00
|
|
|
} while_each_thread(current, tsk);
|
2005-04-17 06:20:36 +08:00
|
|
|
read_unlock(&tasklist_lock);
|
2008-02-08 20:19:06 +08:00
|
|
|
|
2009-06-18 07:27:40 +08:00
|
|
|
notask:
|
2009-06-18 07:27:39 +08:00
|
|
|
retval = wo->notask_error;
|
|
|
|
|
if (!retval && !(wo->wo_flags & WNOHANG)) {
|
2005-04-17 06:20:36 +08:00
|
|
|
retval = -ERESTARTSYS;
|
2008-03-20 10:24:59 +08:00
|
|
|
if (!signal_pending(current)) {
|
|
|
|
|
schedule();
|
|
|
|
|
goto repeat;
|
|
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
end:
|
2009-06-18 07:27:42 +08:00
|
|
|
__set_current_state(TASK_RUNNING);
|
2009-09-24 06:56:46 +08:00
|
|
|
remove_wait_queue(¤t->signal->wait_chldexit, &wo->child_wait);
|
2005-04-17 06:20:36 +08:00
|
|
|
return retval;
|
|
|
|
|
}
|
|
|
|
|
|
2009-01-14 21:14:10 +08:00
|
|
|
SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *,
|
|
|
|
|
infop, int, options, struct rusage __user *, ru)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2009-06-18 07:27:39 +08:00
|
|
|
struct wait_opts wo;
|
2008-02-08 20:19:14 +08:00
|
|
|
struct pid *pid = NULL;
|
|
|
|
|
enum pid_type type;
|
2005-04-17 06:20:36 +08:00
|
|
|
long ret;
|
|
|
|
|
|
|
|
|
|
if (options & ~(WNOHANG|WNOWAIT|WEXITED|WSTOPPED|WCONTINUED))
|
|
|
|
|
return -EINVAL;
|
|
|
|
|
if (!(options & (WEXITED|WSTOPPED|WCONTINUED)))
|
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
|
|
switch (which) {
|
|
|
|
|
case P_ALL:
|
2008-02-08 20:19:14 +08:00
|
|
|
type = PIDTYPE_MAX;
|
2005-04-17 06:20:36 +08:00
|
|
|
break;
|
|
|
|
|
case P_PID:
|
2008-02-08 20:19:14 +08:00
|
|
|
type = PIDTYPE_PID;
|
|
|
|
|
if (upid <= 0)
|
2005-04-17 06:20:36 +08:00
|
|
|
return -EINVAL;
|
|
|
|
|
break;
|
|
|
|
|
case P_PGID:
|
2008-02-08 20:19:14 +08:00
|
|
|
type = PIDTYPE_PGID;
|
|
|
|
|
if (upid <= 0)
|
2005-04-17 06:20:36 +08:00
|
|
|
return -EINVAL;
|
|
|
|
|
break;
|
|
|
|
|
default:
|
|
|
|
|
return -EINVAL;
|
|
|
|
|
}
|
|
|
|
|
|
2008-02-08 20:19:14 +08:00
|
|
|
if (type < PIDTYPE_MAX)
|
|
|
|
|
pid = find_get_pid(upid);
|
2009-06-18 07:27:39 +08:00
|
|
|
|
|
|
|
|
wo.wo_type = type;
|
|
|
|
|
wo.wo_pid = pid;
|
|
|
|
|
wo.wo_flags = options;
|
|
|
|
|
wo.wo_info = infop;
|
|
|
|
|
wo.wo_stat = NULL;
|
|
|
|
|
wo.wo_rusage = ru;
|
|
|
|
|
ret = do_wait(&wo);
|
do_wait: fix sys_waitid()-specific behaviour
do_wait() checks ->wo_info to figure out who is the caller. If it's not
NULL the caller should be sys_waitid(), in that case do_wait() fixes up
the retval or zeros ->wo_info, depending on retval from underlying
function.
This is bug: user can pass ->wo_info == NULL and sys_waitid() will return
incorrect value.
man 2 waitid says:
waitid(): returns 0 on success
Test-case:
int main(void)
{
if (fork())
assert(waitid(P_ALL, 0, NULL, WEXITED) == 0);
return 0;
}
Result:
Assertion `waitid(P_ALL, 0, ((void *)0), 4) == 0' failed.
Move that code to sys_waitid().
User-visible change: sys_waitid() will return 0 on success, either
infop is set or not.
Note, there's another bug in wait_noreap_copyout() which affects
return value of sys_waitid(). It will be fixed in next patch.
Signed-off-by: Vitaly Mayatskikh <v.mayatskih@gmail.com>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Cc: Roland McGrath <roland@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-09-24 06:56:51 +08:00
|
|
|
|
|
|
|
|
if (ret > 0) {
|
|
|
|
|
ret = 0;
|
|
|
|
|
} else if (infop) {
|
|
|
|
|
/*
|
|
|
|
|
* For a WNOHANG return, clear out all the fields
|
|
|
|
|
* we would set so the user can easily tell the
|
|
|
|
|
* difference.
|
|
|
|
|
*/
|
|
|
|
|
if (!ret)
|
|
|
|
|
ret = put_user(0, &infop->si_signo);
|
|
|
|
|
if (!ret)
|
|
|
|
|
ret = put_user(0, &infop->si_errno);
|
|
|
|
|
if (!ret)
|
|
|
|
|
ret = put_user(0, &infop->si_code);
|
|
|
|
|
if (!ret)
|
|
|
|
|
ret = put_user(0, &infop->si_pid);
|
|
|
|
|
if (!ret)
|
|
|
|
|
ret = put_user(0, &infop->si_uid);
|
|
|
|
|
if (!ret)
|
|
|
|
|
ret = put_user(0, &infop->si_status);
|
|
|
|
|
}
|
|
|
|
|
|
2008-02-08 20:19:14 +08:00
|
|
|
put_pid(pid);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
/* avoid REGPARM breakage on x86: */
|
2008-04-11 06:37:38 +08:00
|
|
|
asmlinkage_protect(5, ret, which, upid, infop, options, ru);
|
2005-04-17 06:20:36 +08:00
|
|
|
return ret;
|
|
|
|
|
}
|
|
|
|
|
|
2009-01-14 21:14:09 +08:00
|
|
|
SYSCALL_DEFINE4(wait4, pid_t, upid, int __user *, stat_addr,
|
|
|
|
|
int, options, struct rusage __user *, ru)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2009-06-18 07:27:39 +08:00
|
|
|
struct wait_opts wo;
|
2008-02-08 20:19:14 +08:00
|
|
|
struct pid *pid = NULL;
|
|
|
|
|
enum pid_type type;
|
2005-04-17 06:20:36 +08:00
|
|
|
long ret;
|
|
|
|
|
|
|
|
|
|
if (options & ~(WNOHANG|WUNTRACED|WCONTINUED|
|
|
|
|
|
__WNOTHREAD|__WCLONE|__WALL))
|
|
|
|
|
return -EINVAL;
|
2008-02-08 20:19:14 +08:00
|
|
|
|
|
|
|
|
if (upid == -1)
|
|
|
|
|
type = PIDTYPE_MAX;
|
|
|
|
|
else if (upid < 0) {
|
|
|
|
|
type = PIDTYPE_PGID;
|
|
|
|
|
pid = find_get_pid(-upid);
|
|
|
|
|
} else if (upid == 0) {
|
|
|
|
|
type = PIDTYPE_PGID;
|
2009-04-03 07:58:36 +08:00
|
|
|
pid = get_task_pid(current, PIDTYPE_PGID);
|
2008-02-08 20:19:14 +08:00
|
|
|
} else /* upid > 0 */ {
|
|
|
|
|
type = PIDTYPE_PID;
|
|
|
|
|
pid = find_get_pid(upid);
|
|
|
|
|
}
|
|
|
|
|
|
2009-06-18 07:27:39 +08:00
|
|
|
wo.wo_type = type;
|
|
|
|
|
wo.wo_pid = pid;
|
|
|
|
|
wo.wo_flags = options | WEXITED;
|
|
|
|
|
wo.wo_info = NULL;
|
|
|
|
|
wo.wo_stat = stat_addr;
|
|
|
|
|
wo.wo_rusage = ru;
|
|
|
|
|
ret = do_wait(&wo);
|
2008-02-08 20:19:14 +08:00
|
|
|
put_pid(pid);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
/* avoid REGPARM breakage on x86: */
|
2008-04-11 06:37:38 +08:00
|
|
|
asmlinkage_protect(4, ret, upid, stat_addr, options, ru);
|
2005-04-17 06:20:36 +08:00
|
|
|
return ret;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#ifdef __ARCH_WANT_SYS_WAITPID
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* sys_waitpid() remains for compatibility. waitpid() should be
|
|
|
|
|
* implemented by calling sys_wait4() from libc.a.
|
|
|
|
|
*/
|
2009-01-14 21:14:10 +08:00
|
|
|
SYSCALL_DEFINE3(waitpid, pid_t, pid, int __user *, stat_addr, int, options)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
|
return sys_wait4(pid, stat_addr, options, NULL);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#endif
|